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

Annotations give readOnlyHint=true and the description reinforces it with 'Non-mutating computation', clarifying that the POST is a computation rather than a write. It also discloses the return payload (triage level plus serious/emergency observations), which matters because there is no output schema.

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-loaded with the outcome and its enumerated values, followed by the non-mutation note and a compact engine reference. Every sentence earns its place, though the raw endpoint ('POST /triage') is slightly incidental.

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 6-parameter nested-object tool with no output schema, the description usefully names the returned triage level and observations. It stops short of clarifying required-parameter interaction (sex/age) or how partial evidence affects results.

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 83%, so the schema already documents age, sex, evidence, extras, dev_mode, and model_id. The description adds no syntax or format detail beyond the schema and only hints that 'evidence' drives the result. Baseline 3 applies.

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 ('Recommend a triage level') plus the exact enumeration of possible outputs, and names the resource (triage). It is clearly separable from sibling infermedica_diagnosis and the rest of the get/list tools.

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 'given the evidence' implies a precondition (evidence must already exist, e.g. from infermedica_parse/suggest) but never states when to pick triage over diagnosis or recommend_specialist. Usage is only implied.

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