run_doctor

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

Annotations provide readOnlyHint=true, and the description reinforces this by framing the operation as a health check rather than a mutation. Beyond the annotation, it adds valuable behavioral detail: connection failures include classified diagnoses (authentication_failed vs bridge_unreachable) with fixes, the tool reports version and entrypoint path, and it warns that other health fields can remain healthy even when an orphaned install shadows an upgrade. This is substantial added context beyond structured metadata.

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 front-loaded with the core purpose, then adds the key environmental warning and failure-classification detail, and ends with a direct routing instruction to the lighter sibling. Every sentence carries distinct information — coverage scope, extra version/path reporting, diagnostic output, intended use, and alternative tool — with no filler or repetition.

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 complex diagnostic tool with no output schema, the description provides enough context to invoke it correctly: what it checks, optional behaviors, failure output characteristics, and when to prefer a different tool. It also explains why the version/path reporting matters, addressing an important operational scenario. Nothing essential is missing for an agent to select and call this tool.

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?

Schema description coverage is 100%, so the input schema already documents all four parameters clearly. The description adds some high-level context by mentioning the optional IMAP IDLE probe and connection diagnosis, but it does not add parameter-level meaning beyond what the schema provides. Baseline 3 is appropriate because the description isn't needed to compensate for schema gaps.

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 opens with a specific verb-resource pair ('Run a comprehensive production health check') and enumerates the exact coverage areas: SMTP auth, IMAP auth, IMAP IDLE probe, SQLite index integrity, sync-failed drafts, runtime policy validation, and capabilities. It also explicitly distinguishes itself from get_connection_status by positioning this as the full diagnostic tool, so there is no ambiguity about its role relative to siblings.

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?

Usage guidance is explicit: 'Use to fully diagnose or validate the setup' and 'Prefer get_connection_status for a quick protocol-only reachability check.' It also gives a concrete trigger scenario — checking this tool first when behavior doesn't match the changelog because an old install can shadow an upgrade. This tells an agent exactly when to choose this tool and when to pick an alternative.

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