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

Annotations only declare readOnlyHint=true; the description reinforces this with 'Non-mutating computation' and resolves the ambiguity of a POST endpoint that does not mutate state. It also discloses exactly what the call returns, which the annotations do not cover. It stops short of mentioning auth requirements, rate limits, or model/version behavior.

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 front-loaded sentences with no filler; the return payload is stated before the endpoint note. The trailing 'Engine API: POST /diagnosis' is marginally redundant but does usefully reinforce that a POST can still be non-mutating.

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?

With no output schema, the description correctly takes on the burden of describing return values (next question, ranked conditions with probabilities, should_stop flag), and the 100%-covered input schema handles the nested evidence objects. The main remaining gap is the multi-step loop and its relationship to sibling tools, which an agent must infer.

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 schema already documents all six parameters including evidence items, model_id, dev_mode, and extras. The description adds no parameter-level detail such as evidence shape, header mapping, or how extras flags affect engine behavior, so baseline 3 is appropriate.

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 ('Run the diagnostic engine over the collected evidence') and enumerates the three outputs an agent receives: next question, ranked candidate conditions with probabilities, and a should_stop flag. It does not explicitly distinguish itself from closely related siblings such as infermedica_triage, infermedica_rationale, or infermedica_explain, which also operate over the same evidence, so an agent must infer the boundary.

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?

The phrase 'over the collected evidence' plus the schema note that evidence 'may be empty for the first call' implies the iterative diagnose loop, but there is no explicit when-to-use or when-not-to-use guidance relative to infermedica_suggest, infermedica_triage, or infermedica_rationale. Usage is implied rather than stated.

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