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

Annotations already declare readOnly, non-destructive, open-world behavior, so the bar is lower; the description still adds genuine context: pagination semantics tied to the previous reply's next_start, and a health-data warning that responses contain patient ids. It stops short of describing the payload shape or handling of empty ranges.

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?

Three compact, front-loaded clauses: scope, filtering, pagination, then the health-data caveat. No filler and nothing buried at the end.

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 14-parameter, no-output-schema list tool, the description covers filtering, paging, conditional required dates, and the sensitive-data caveat. The response field list is unspecified, but the next_start contract gives enough to iterate correctly.

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 64% across 14 params, and the description compensates by enumerating the filterable dimensions (professional, patient, unit, location, specialty, channel, procedure, status) and the conditional-nullity of date_from/date_to and the start/next_start pairing, adding meaning beyond the bare schema.

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 the exact resource (appointments), the two access modes (date range or single id), and the full filter axis set, so it is unmistakably the read/list tool among siblings like feegow_create_appointment and feegow_get_available_schedule.

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?

Explains the date requirement shim (dates required unless appointment_id is given), tells the caller to page with next_start, and routes to feegow_list_units, feegow_list_booking_channels and feegow_list_appointment_statuses for id resolution. It does not contrast itself with any alternative read tool, but there is no close sibling that overlaps.

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