UK Data: UK food hygiene ratings

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description only needs to add context. The '(cost: 1 credit)' note is genuinely useful billing information not present in annotations, and the return-field list is helpful with no output schema. However, it says nothing about default result count, sorting, or what happens when no filters are supplied despite openWorldHint=true implying unbounded results.

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 tight sentences and a parenthetical: purpose first, filterable facets second, return payload third, cost last. Nothing is repeated from the schema or annotations and every clause carries information.

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 9-parameter, zero-required, no-output-schema search tool, the description covers purpose, inputs, outputs and cost adequately. The remaining gaps are operational details (default limit, pagination, filter combination rules) rather than anything that would cause a call to be constructed wrongly.

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 100%, so the baseline is 3, and the description only mildly improves on it by mapping plain-language facets to parameters ('council' → localAuthorityId, 'type' → businessTypeId, 'radius' → radiusMiles paired with latitude/longitude). It does not explain the rating token format (e.g. fhrs_5_en-gb), the 1-500 limit, or whether filters combine with AND semantics.

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 names a specific verb and resource ('search food businesses') against a named dataset ('Food Standards Agency hygiene ratings') and enumerates the facets that can be searched. It is clear about what it does, but it never contrasts itself with the nearby food_alerts sibling or with cqc_search, leaving the agent to infer the boundary from the dataset name alone.

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 is only implied through the filter list ('by name, address, council, type, rating or radius'), which signals that all parameters are optional filters. There is no statement about when this tool is preferable to food_alerts, nor whether at least one filter is required, so the agent must guess at edge-case behaviour.

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