doctor

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

No annotations exist, so the description carries the full burden; "Check" implies a non-mutating probe and the parenthetical "(never shown)" usefully discloses that the API key is redacted from output. However, it never states whether the tool has side effects, whether it can repair what it finds, or what form the report takes, which are exactly the gaps annotations would normally fill.

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?

A single front-loaded sentence with a compact enumeration of the four checks; no filler. Slightly clipped to the point of ambiguity, but every clause earns its place.

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?

For a zero-parameter, no-output-schema diagnostic tool, the agent still needs to know whether this is a safe read-only probe and how to act on the results, neither of which is covered. Adequate to identify the tool, insufficient to complete the troubleshooting loop.

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 tool takes zero parameters, so the baseline is 4; there is nothing parameter-level for the description to clarify or omit.

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 gives a specific verb ("Check") and enumerates the exact subsystems inspected: engine install, Python deps, API key, backend status. That is far more informative than the bare name "doctor", though it never distinguishes itself from look-alike siblings such as setup, provider_setup, or start_backend.

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 implies a diagnostic/troubleshooting role but never states when to run it (e.g., before start_backend, after install, when a run fails) or when to prefer setup/quickstart instead. No exclusions or alternatives are named, so the agent must infer the workflow placement.

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