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

Annotations already cover read-only, idempotent, non-destructive and open-world, so the bar is lower — yet the description adds substantial non-obvious context: geocoding is done via postcodes.io with 'nothing else leaves PetCare Atlas', listings come from public professional registers, and 'Nobody pays to be listed or ranked.' Provenance, privacy and neutrality disclosures are exactly the kind of behavior an agent cannot infer from structured fields.

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-loads purpose, then emergency behavior, then returned fields, then provenance — a sensible priority order. The closing trust statements ('Nobody pays to be listed or ranked', 'No clinical advice') are slightly padded but still relevant to how an agent should present results.

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 7-parameter tool with no output schema, the description usefully enumerates returned fields (name, id, type, town, postcode, distance, phone, accreditations, page link) and covers emergency mode and data provenance. The only meaningful gap is the absence of routing guidance toward provider_details for deeper single-provider lookups.

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. The description still adds meaning beyond the schema by explaining that results are ordered 'nearest first' and that the place input is resolved to coordinates via a public postcode service, which clarifies how the required 'place' parameter is interpreted.

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 with scope: 'Find UK vet practices, vet hospitals, specialists and accredited practitioners ... near a place, nearest first.' An agent can immediately tell this is a proximity search over a provider directory. It never names the sibling it is not (e.g. provider_details for a single listing), so sibling differentiation is only implied by the summary-return sentence.

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 clear context for the emergency variant ('An emergency search starts with a fixed safety line and lists RCVS-accredited emergency service clinics and the nearest vets') and a scope boundary ('No clinical advice'). There is no explicit when-to-use/when-not statement or named alternative such as provider_details for full profile lookup, 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.