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

The annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context that annotations and schema do not: results are paginated by record ID and ordered newest-first, which affects how an agent pages and how it should interpret ordering. It does not state the page-size cap or how to obtain the next cursor, keeping it below a 5.

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 tight sentences with no filler, and the return-content summary is front-loaded ahead of the pagination detail. Minor redundancy: since an output schema exists, listing the returned fields partially duplicates structured data, though it still serves as quick orientation.

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 values are adequately covered, but for a 7-filter listing tool the definition says nothing about how the filters behave or when to reach for this versus its siblings. It is minimally sufficient to invoke, not sufficient to invoke 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?

Seven parameters exist with only 57% schema description coverage, and the description explains none of them. The undocumented ones (limit, cursor, biomarker_code) get no clarification in prose, and there is no explanation of how search, date_from/date_to, report_id and biomarker_code interact or compose. The description does not compensate for the coverage gap at all.

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?

"Read your biomarker values, measurement dates, units and reference values" gives a specific verb (read) and a specific resource (biomarker observations), and it tells the agent what data comes back. It stops short of differentiating itself from the sibling list_lab_reports / get_lab_report, so an agent must infer that observations are the per-biomarker rows inside a report rather than the reports themselves.

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?

There is no when-to-use guidance at all: nothing says whether to call this instead of list_lab_reports, whether a report_id should usually be supplied, or which filters to combine. The only operational hint is the pagination sentence, which describes mechanics rather than selection criteria.

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