reproduce_run

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

The description states it will 'rerun' and 'compare' but discloses no behavioral details beyond that. For a mutation tool (readOnlyHint=false), it does not explain side effects (e.g., does it overwrite outputs? create logs? require specific permissions?). The minimal description adds little beyond what annotations already provide.

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?

The description is a single sentence, which is concise, but it lacks structure and does not front-load critical information. It is not overly wordy, but it fails to earn its place by providing sufficient detail. A score of 3 reflects it is adequate in length but not optimally informative.

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 the tool has 4 parameters, no output schema excerpt shown, and 17 sibling tools, the description is incomplete. It does not explain the comparison format, what 'result JSON hashes' means, or any preconditions (e.g., the previous run must exist). The agent would need additional context to use this tool correctly.

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?

The input schema has 4 parameters but the description adds no meaning to any of them. Schema description coverage is 0% (the schema itself has some descriptions for config_path and project_root, but the tool description provides none). The agent must rely entirely on the schema, which has gaps (e.g., run_id has no description).

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's purpose: rerun a previous script and compare result JSON hashes. It uses specific verbs ('rerun', 'compare') and identifies the resource ('previous saved input script'). However, it does not differentiate from sibling tools like run_did or run_iv, which are more specific analyses; the differentiation relies on the tool name rather than the description.

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?

The description implies usage for reproducing previous runs but provides no explicit guidance on when to use this tool versus creating a new run via sibling tools (e.g., run_did, run_regression_fixest). There are no when-not statements or alternative recommendations, leaving the agent to infer context from the tool name alone.

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