diff --git a/prompts/tools-file.md b/prompts/tools-file.md
index ab005ff..b42ed3e 100644
--- a/prompts/tools-file.md
+++ b/prompts/tools-file.md
@@ -14,19 +14,20 @@
 
 **Calling convention**:
 ```
-execute_code: steps=[{tool: "file_read",  args: ["/abs/path", start, end]}]              # segment (preferred)
-execute_code: steps=[{tool: "file_read",  args: ["/abs/path"]}]                           # whole file (≤2000 lines)
-execute_code: steps=[{tool: "file_write", args: ["/abs/path", "content"]}]
-execute_code: steps=[{tool: "file_edit",  args: ["/abs/path", "old", "new"]}]
-execute_code: steps=[{tool: "file_glob",  args: ["src/**/*.go"]}]
-execute_code: steps=[{tool: "file_grep",  args: ["func.*Handler", "src/"]}]
+call_tool: file_read ["/abs/path", start, end]              # segment (preferred)
+call_tool: file_read ["/abs/path"]                           # whole file (≤2000 lines)
+call_tool: file_write ["/abs/path", "content"]
+call_tool: file_edit ["/abs/path", "old", "new"]
+call_tool: file_glob ["src/**/*.go"]
+call_tool: file_grep ["func.*Handler", "src/"]
 ```
 
 **Returns**: file contents with line numbers / match results / write confirmation.
 
 **Batch independent reads** in a single call for parallel execution:
 ```
-execute_code: steps=[{tool: "file_read", args: ["a.go", "1", "50"]}, {tool: "file_read", args: ["b.go", "1", "50"]}]
+call_tool: file_read ["/a.go", "1", "50"]
+call_tool: file_read ["/b.go", "1", "50"]
 ```
 
 **Prefer segments over full-file reads.** Use `file_grep` or `file_glob` to locate the relevant section, then read only the lines you need with `start`/`end`. Full-file reads are for small files or when you need the whole content.
diff --git a/prompts/tools-lsp.md b/prompts/tools-lsp.md
index 4667276..2ca4869 100644
--- a/prompts/tools-lsp.md
+++ b/prompts/tools-lsp.md
@@ -16,13 +16,13 @@ Code intelligence via language servers (gopls, clangd, intelephense). The bridge
 
 **Calling convention**:
 ```
-execute_code: steps=[{tool: "lsp_definition",  args: ["/abs/path/to/file.go", "42", "10"]}]
-execute_code: steps=[{tool: "lsp_references",  args: ["/abs/path/to/file.go", "42", "10"]}]
-execute_code: steps=[{tool: "lsp_hover",       args: ["/abs/path/to/file.go", "42", "10"]}]
-execute_code: steps=[{tool: "lsp_rename",      args: ["/abs/path/to/file.go", "42", "10", "NewName"]}]
-execute_code: steps=[{tool: "lsp_symbols",     args: ["/abs/path/to/file.go"]}]
-execute_code: steps=[{tool: "lsp_diagnostics", args: ["/abs/path/to/file.go"]}]
-execute_code: steps=[{tool: "lsp_completion",  args: ["/abs/path/to/file.go", "42", "10"]}]
+call_tool: lsp_definition ["/abs/path/to/file.go", "42", "10"]
+call_tool: lsp_references ["/abs/path/to/file.go", "42", "10"]
+call_tool: lsp_hover ["/abs/path/to/file.go", "42", "10"]
+call_tool: lsp_rename ["/abs/path/to/file.go", "42", "10", "NewName"]
+call_tool: lsp_symbols ["/abs/path/to/file.go"]
+call_tool: lsp_diagnostics ["/abs/path/to/file.go"]
+call_tool: lsp_completion ["/abs/path/to/file.go", "42", "10"]
 ```
 
 **Line/col are 1-indexed** — matching `file_read` output. Use the line numbers from `file_read` directly.
@@ -35,5 +35,7 @@ execute_code: steps=[{tool: "lsp_completion",  args: ["/abs/path/to/file.go", "4
 
 **Parallel reads**: all read-only LSP tools can be batched in a single call:
 ```
-execute_code: steps=[{tool: "lsp_hover", args: [...]}, {tool: "lsp_symbols", args: [...]}, {tool: "lsp_completion", args: [...]}]
+call_tool: lsp_hover [...]
+call_tool: lsp_symbols [...]
+call_tool: lsp_completion [...]
 ```
diff --git a/prompts/tools-memory.md b/prompts/tools-memory.md
index 92c7e40..ec5e16d 100644
--- a/prompts/tools-memory.md
+++ b/prompts/tools-memory.md
@@ -8,7 +8,7 @@ Persist a fact that would otherwise be lost when the session ends.
 
 **Calling convention**:
 ```
-execute_code: steps=[{tool: "memory_remember", args: ["<title>", "<tags_csv>", "<body>"]}]
+call_tool: memory_remember ["<title>", "<tags_csv>", "<body>"]
 ```
 - `title`: short noun phrase
 - `tags_csv`: comma-separated tags; pick specific and reusable terms
@@ -33,7 +33,7 @@ Search stored memories for relevant context.
 
 **Calling convention**:
 ```
-execute_code: steps=[{tool: "memory_recall", args: ["<query>"]}]
+call_tool: memory_recall ["<query>"]
 ```
 - `query`: keyword, tag, or phrase — searches both filenames and body content
 
diff --git a/prompts/tools-reasoning.md b/prompts/tools-reasoning.md
index 4596004..a6eb00d 100644
--- a/prompts/tools-reasoning.md
+++ b/prompts/tools-reasoning.md
@@ -6,7 +6,7 @@ A scratchpad for externalizing reasoning. The thought is recorded in conversatio
 
 **Calling convention**:
 ```
-execute_code: steps=[{tool: "reasoning_think", args: ["your full reasoning here"]}]
+call_tool: reasoning_think ["your full reasoning here"]
 ```
 
 **Returns**: nothing. The value is entirely in writing the thought.
diff --git a/prompts/tools-task.md b/prompts/tools-task.md
index 029ba81..1e8f3fa 100644
--- a/prompts/tools-task.md
+++ b/prompts/tools-task.md
@@ -6,9 +6,9 @@ A session-scoped markdown checklist at `s/$OLLIE_SESSION_ID/plan`. Survives comp
 
 **Calling convention**:
 ```
-execute_code: steps=[{tool: "task_add",   args: ["step one", "step two", "..."]}]
-execute_code: steps=[{tool: "task_check", args: []}]
-execute_code: steps=[{tool: "task_clear", args: []}]
+call_tool: task_add ["step one", "step two", "..."]
+call_tool: task_check []
+call_tool: task_clear []
 ```
 
 **Returns**: confirmation.