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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial context beyond them: every row carries at least one retrievable source with a verbatim quote, section locator and content hash, and paid standards/copyrighted books are represented by metadata only with body text never reproduced. The 'absence is not safety' warning is a behavioral trait no annotation conveys.

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?

Front-loads purpose before guidelines, limits and examples, and every section adds genuine information. It is on the verbose side and the example list is somewhat repetitive, but no sentence is wasted.

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 needn't explain return values, yet it still clarifies the verdict vocabulary and citation payload. Combined with the scope limits and safety caveat, an agent has everything needed to call this correctly and interpret the results responsibly.

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 description coverage is 100%, so the schema already documents all seven parameters including id formats, enums and defaults. The description largely restates this (id prefixes fit-ex-*/fit-cond-*, Chinese/English keywords, verdict filtering) rather than adding new syntax or semantic depth, so the 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+resource: look up an exercise x condition pair and return a graded verdict plus verbatim source quote, locator and content hash. It explicitly positions itself against the rest of the fitness domain ('is this movement contraindicated' rather than 'what should I train'), distinguishing it from siblings like query_activity_guidelines and get_dietary_guidelines.

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?

The Guidelines and Limits sections state how to query (id like fit-ex-* or keyword in Chinese/English, optional verdict filter), what the tool will not do (no individualised advice, no diagnosis, no dosing), and the critical caveat that absence of a pair is not evidence of safety. Four concrete call examples reinforce the usage patterns.

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