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

Annotations already declare the safe-read profile (readOnly, idempotent, non-destructive, closed world), and the description still adds meaningful behavior beyond them: a hard cap of 5 results, AND-matching over name words in any order, and a privacy rule that phone digits are only partially exposed to disambiguate namesakes. That result-truncation and masking detail is not derivable from the annotations or 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?

Three tight sentences: trigger condition first, result contract second, exclusions last. Every clause carries information and none of it repeats the title or annotations.

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?

With an output schema present, the description need not detail return values, yet it still sketches the shape (ids, clinic, partial phone) enough to set expectations about truncation and masking. For a 2-parameter lookup tool this is fully sufficient to call 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 100%, and the schema's own description already covers the 'every word must appear, any order, ignoring case and accents' semantics, which the description largely restates. The description adds the truncation behavior implicit in the search (only 5 hits) but says nothing about clinicId, so it neither extends nor detracts from the 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?

The description names a specific verb (find) and resource (patient) and immediately narrows the scope: 'Returns up to 5 patients whose name contains every word given, with their ids and clinic.' The closing clause 'Not for browsing, counting or reading patient records' separates it from the list_* and record-reading siblings.

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?

It gives an explicit triggering condition ('when someone names a patient to book, move, cancel or update') and explicit exclusions ('Not for browsing, counting or reading patient records'). What it lacks is naming the concrete alternatives to reach for instead, e.g. list_appointments or show_clinic_overview, so the when-not is stated as a category rather than a route.

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