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

Annotations already declare readOnlyHint=true, so 'Non-mutating computation' largely restates the structured safety signal. The useful added context is that it reuses the diagnosis/triage request body and targets the /recommend_specialist endpoint, but nothing is said about return shape, evidence requirements, or model/Dev-Mode header effects.

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?

Three short sentences, zero filler, with the core purpose front-loaded before the non-mutation note and the endpoint. Nothing needs to be trimmed.

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 computation tool with rich schema coverage, an existing readOnly annotation, and no output schema, the description conveys purpose, input reuse, and mutability adequately. It stops short of describing the returned specialist/channel payload, which is the one remaining gap given there is no output schema.

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 every parameter (age, sex, evidence, extras, dev_mode, model_id) is already documented in the schema. The description only adds that the body matches diagnosis/triage, which is a mild framing hint rather than parameter-level meaning.

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 ('Recommend') and resource ('the most appropriate medical specialist and consultation channel'), which cleanly separates it from siblings like infermedica_diagnosis and infermedica_triage. It also pins the underlying endpoint (POST /recommend_specialist), but it does not explicitly contrast itself against those siblings.

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 states the tool operates on 'the collected evidence' and accepts the same body as diagnosis/triage, which implies it is used on the same evidence payload. However it never says when to choose specialist recommendation over diagnosis or triage, or what prerequisites are needed.

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