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

Annotations already declare read-only/idempotent/closed-world, and the description still adds material behavior: phone numbers are dropped at ingest, registered-manager names are never ingested, 1 credit per call with an API key, and a keyless preview capped at 5 rows / 20 calls per day. Cost, rate limits, and data-completeness caveats are exactly the traits annotations cannot express.

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 resource, then result fields, provenance, and caveats — each sentence carries content. It is dense and slightly list-heavy, but there is almost 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?

No output schema exists, so the description compensates by enumerating returned fields and the stable CQC location id key. Cost, quota, and data-exclusion caveats are covered; the main remaining gap is the meaning/format of the pagination and niche filter parameters.

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?

With 15 parameters at 0% schema description coverage the description carries the burden, and it only partly does: it clarifies that q searches all text fields and that filters AND together, and lists filterable facets (service types, specialisms, provider, address, local authority, region, latest check date). It says nothing about the semantics of page, per_page, website_present, outward_code, or the accepted values for specialisms/service_types.

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?

States a specific verb (query) plus an exact resource (CQC-regulated health and social care locations in England) and enumerates the entity types covered. It is unmistakably distinct from siblings like query_nhs_ods or query_uk_charities, which target different registries.

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?

Explains how the tool is used mechanically — 'Filters combine with AND; q searches all text fields' — and gives cost/quota conditions for keyed vs keyless calls. It does not, however, tell the agent when to prefer a sibling (e.g., NHS ODS for organisation reference data), so routing guidance is left to inference.

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