rms_doctor

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

No annotations are supplied, so the description carries the full burden. It does well on side effects: it discloses the daily update check, the RMS_MEMORY_NO_UPDATE_CHECK=1 opt-out, the replaced-binary detection, and that frontmatter repair refuses sticky-bind cases. However, it never states whether the default (no repair_frontmatter) run is purely read-only or whether it writes a report/cache, which is the key safety question for a diagnostics tool.

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?

Front-loaded with purpose and the check list, then conditional/edge-case behavior in later sentences. The long semicolon-separated parenthetical is dense but each item is informative rather than filler.

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 two-parameter diagnostics tool with no output schema, the description covers scope, mutation guardrails, and background side effects. It says 'Returns structured JSON' but does not sketch the report shape, which is the main remaining gap.

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 coverage is 100%, so both parameters are already documented, including the 'requires project' rule. The description restates the constraint and adds the sticky-bind refusal nuance, but contributes little semantic detail beyond the schema.

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?

Opens with a specific verb+resource ('Run the vault health diagnostics') and enumerates the checks performed (structure, IDs, links, LanceDB, wiki isolation, registry, freshness, credentials), so the agent knows exactly what this does. It does not explicitly distinguish itself from the closest sibling, rms_hygiene, but the enumeration makes the scope unambiguous.

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?

Gives conditional guidance for the repair path ('only with an explicit project') and explains the update-check behavior, but never states when to choose this over rms_hygiene or rms_prune, nor what a typical 'healthy vs unhealthy' workflow looks like. Usage is implied by the description of what gets checked.

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