Quick look at a few lab values (made-up or de-identified numbers)

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior. The description goes well beyond them by disclosing latency profile (local check, no engine round-trip), the non-diagnostic nature of the output, and a precise data-retention policy including the 30-minute claim-link window and deletion of unclaimed values.

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 core purpose and the alternative-tool routing are front-loaded in the first two sentences. The retention sentence is long and slightly heavy for its position, but it carries substantive privacy information rather than 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?

An output schema exists, so return-value explanation is unnecessary. Given a one-parameter tool with full schema coverage and complete annotations, the description still supplies privacy constraints, the alternative path, and what the result means clinically—nothing an agent needs to call it safely is missing.

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 100% and the single nested parameter is documented with an inline example, so the schema carries the semantics. The description's biomarker examples ('A1c, eGFR, LDL') loosely map to the schema but add no format or naming rules beyond it, so 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 and resource ('fast first look at a few lab values'), names the concrete outputs (A1c, eGFR, LDL flagged against PRISM reference ranges), and scopes it with 'not a diagnosis.' It is clearly separable from explain_my_lab_results and full_prism_report 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?

Explicit routing: use explain_my_lab_results for guideline-cited suggestions, use this for a quick reference-range check on synthetic/de-identified data only. It also states a hard exclusion ('Do NOT submit PHI'), which is exactly the kind of when-not guidance agents need.

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