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

With no annotations the description carries the full burden, and it does disclose real behavior: results are ranked with promoted listings first, and the ambiguous-city case returns needs_state: true with zero clinics plus a candidates array containing the exact next_call arguments. It omits auth requirements, rate limits, and pagination behavior tied to `limit`, which keeps it short of a 5.

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?

The purpose is front-loaded in sentence one, and the denser final sentence is justified because it documents the non-obvious error path. It is slightly heavy for a four-parameter lookup, but no sentence is 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?

There is no output schema, so the description must describe return values, and it does: the ranked shortlist fields, the promoted-listing ordering, and the exact degraded-response shape when the city is ambiguous. An agent has everything needed to call it and recover from the one failure mode.

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 75%, so the baseline is around 3, but the description adds functional meaning the schema only hints at: the concrete consequence of omitting `state` (cross-state resolution, the needs_state contract, and the shape of the recovery payload). `limit` remains unexplained in both places, which is a minor gap.

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 first sentence states a specific verb (find) plus the resource (veterinary specialty clinics) and the two required dimensions (city + specialty). It then enumerates the return payload, which cleanly separates it from siblings like get_clinic (single record) and find_specialists_by_procedure. An agent can route to it without opening any schema.

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?

It gives explicit conditional guidance for the `state` parameter (omit it unless you know it; the result tells you when disambiguation is required) and even points at the follow-up call to make. It does not, however, contrast itself against siblings such as find_specialists_by_procedure or get_clinic, so the when-to-prefer-this-tool guidance is incomplete.

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