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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety profile is covered. The description adds real value beyond that: it discloses the four-bucket output shape, that warning signs accompany the answer, that it is not a diagnosis, and that it deliberately errs toward safety — the last point meaningfully calibrates how an agent should present results.

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?

One dense sentence plus a short disclaimer, with the outcome categories front-loaded and the caveat trailing. No filler, though the semicolon-chained clauses are slightly harder to parse than separate sentences would be.

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 correctly takes on the job of naming the four possible answers and the warning-signs component. But for a 5-parameter tool at 20% schema coverage, it leaves the non-symptom inputs entirely unexplained, so an agent lacks enough to call it well.

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 only 20% (just the 'duration' example), and the description says nothing about any parameter. It never explains why age, pregnant, or language matter, even though age and pregnancy materially change triage output — an agent could easily omit them. This is the clearest gap in the definition.

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 input (symptoms) and a specific output taxonomy: emergency now, clinician within 24 hours, clinician in a few days, or home care, plus warning signs. That taxonomy distinguishes it clearly from the informational siblings (explain_lab_report, explain_prescription, find_clinics_near), which do not triage urgency.

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?

Usage is implied by the framing 'given symptoms, gives the safe next step', but there is no explicit routing guidance or exclusion. Notably it never says a person with an actual emergency should call emergency services instead of using the tool, nor how this differs from explain_lab_report or find_clinics_near in a workflow.

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