Run macro script

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description reveals key behaviors: dispatching through handlers, dry-run planning, error halting, raw Python opt-in with server-side gate, and potential failure of redacted args. It does not explicitly state side effects but enough context is provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two well-structured sentences: first states purpose and lists parameters, second adds a crucial warning. No redundant information, front-loaded with key details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema or annotations, the description omits what the tool returns or any success/failure signals. For a complex tool with nested objects, it covers usage but not results or error behavior beyond stopOnError.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 0% schema coverage, the description explains most parameters meaningfully (e.g., 'shallow-merge per-tool arg replacements' for argsOverrides). It doesn't explicitly link macroPath to the file path, but the context is clear.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool replays a MacroRecord JSON file by dispatching entries through tool handlers, specifying both the action and resource. It implicitly differentiates from sibling 'macro_recorder' which records macros.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains when to use each parameter (dryRun, stopOnError, argsOverrides, allowRawPython) and warns about redacted args. However, it lacks explicit guidance on when not to use this tool versus alternatives like manual replay.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.