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

Annotations already establish read-only, idempotent, non-destructive behavior, yet the description still adds substantive context: provenance and refresh cadence (official weekly CQC care directory), the stable key (CQC location id), and deliberate data omissions (phone numbers dropped at ingest, registered-manager names never ingested) that would otherwise surprise an agent. Billing and preview rate limits are also disclosed up front.

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?

It is a single dense block, but front-loaded with what the dataset contains before dropping into operational caveats, and nearly every clause carries information (coverage, provenance, key, omissions, filter logic, cost, limits). Only the enumeration of care-setting types runs slightly long relative to its value.

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 15-filter tool with no output schema, the description compensates by listing the record fields returned (service types, specialisms, provider, address, area, local authority, region, latest check date) and by covering cost, preview limits, and data omissions. Remaining gaps are pagination behavior and accepted values for the categorical string filters, which an agent must guess.

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 0% across 15 parameters, so the description carries the full burden and only partially meets it: it explains that q searches all text fields and that filters AND together, and it lists record fields that roughly map to filter names. Nothing explains expected value vocabularies for service_types, specialisms, region or local_authority, nor the odd string-typed website_present filter, nor pagination semantics (page/per_page defaults and the 100 cap).

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 and resource ('query ... every health and social care location regulated by CQC in England') and enumerates the covered entity types (hospitals, care homes, GP practices, dentists, homecare, hospices, ambulance). The dataset identity — CQC England, official weekly care directory, keyed by CQC location id — cleanly separates it from the other query_uk_* siblings (charities, companies, schools, planning, etc.).

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 operational context for choosing it: official weekly CQC source, cost of 1 credit per call, and a no-key preview of 5 rows capped at 20 calls/day. It also states that filters combine with AND and that q searches all text fields, which tells an agent how to compose a query. It does not name an alternative tool or state when not to use it, so it stops short of full routing guidance.

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