doctor

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description does not need to restate safety. It adds value beyond annotations by describing what the check covers and framing it as a first-line diagnostic. No contradiction with the read-only annotation; the tool plainly inspects configuration rather than mutating it.

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 short sentences deliver the core function, the specific checks performed, and the precise usage context. There is no filler or redundant restatement of the tool name. The description is front-loaded and every sentence 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 simple read-only diagnostic with one optional parameter, the description is complete enough: it names the exact problems it detects and when to run it. It does not describe the return format, but the absence of an output schema and the nature of the tool make this a minor gap rather than a critical omission.

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 single parameter 'repo' has full schema description coverage ('path to the scored repo's root (default: the repo the server was started in)'). The tool description does not add parameter-level detail, but with 100% schema coverage, the schema already carries the necessary meaning. Baseline 3 is appropriate.

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 identifies the tool as a diagnostic check for config and repo agreement, enumerating specific failure modes it detects (typo keys, empty scopes, missing lane cwds, unresolvable runners). This is far more specific than a generic tool name and gives an agent a concrete model of the tool's function, distinguishing it from analysis-oriented siblings like coupling or duplication.

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 second sentence gives explicit trigger conditions: 'Run it first when any other tool answers strangely or an expected file is missing from the ranking.' This tells the agent exactly when to invoke doctor versus other tools, which is ideal usage guidance for a diagnostic tool.

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