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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description earns credit by disclosing output behavior beyond that: it returns ranked candidate causes with discriminators and an ordered check list, modifies its breadth on ambiguous input, and explicitly refuses a verdict ('does not say which cause it is') — a crucial expectation setter.

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 the verb and resource, and every clause carries information — the matched resource, the returned content, and the ambiguity caveat. It is a single run-on sentence, which slightly hurts scanability, but there is no 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?

With an output schema present, the description needn't re-explain return values, and it still sketches the shape of the answer. Combined with 100% parameter coverage and full annotation coverage, the definition is complete enough to invoke correctly; only routing guidance versus siblings is thin.

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%, and each of the four parameters (symptom, limit, detail, market) already carries a rich inline description, so the schema does the heavy lifting. The description adds no parameter-level detail (nothing about the limit=3 cap, the full/summary modes, or the market effect), which is acceptable at this coverage but adds no extra value.

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?

Specific verb+resource: matches a plain-words building defect (crack, damp, leak, tripping breaker) to the site's diagnosis pages. It also names the concrete payload (candidate causes, distinguishing signs, ordered checks, when to call a professional), which no sibling tool offers.

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 context is implied by 'described in plain words' and the ambiguity note ('ambiguous words return candidates'), so an agent can infer it wants free-text symptom input. But no alternatives are named and no when-not guidance is given, e.g. what to do when a calculator-style sibling (get_calculator, calculate) would be the better fit.

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