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

Annotations already declare read-only, idempotent, non-destructive behavior. The description adds useful context beyond that: results are sorted nearest first, include phone channels, hours, open status, rating, and price when treatment_id is used.

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 sentences with no waste. Purpose and ordering come first, followed by returned fields and accepted inputs, making the definition easy to scan.

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?

Given 10 parameters, an output schema, and read-only annotations, the description covers the core purpose, key inputs, and return contents. It omits pagination and some filter semantics, but the schema and output schema fill those gaps.

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 80%, so most parameter meaning is already in structured fields. The description adds some value by explaining the near/place alternative and treatment_id's price output, but it does not clarify other parameters like page, radius_km, open_on, or open_now.

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 states a specific verb and resource (find clinics) with clear scope: near a place, in a town, or by name, nearest first. It also previews returned fields. It does not explicitly differentiate itself from siblings like get_clinic or find_practitioners, so it stops short of a 5.

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 explains that you should give near or place and that treatment_id narrows to clinics offering that treatment now. However, it gives no explicit when-to-use versus alternatives (e.g., get_clinic for a single clinic) and no when-not guidance.

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