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

Annotations already signal read-only, idempotent, and non-destructive behaviour, so the bar is lower. The description adds useful context: results are public and cached for 7 days per pair, and the response includes an AI-written synthesis. It doesn't explain caching invalidation or auth requirements, but that is minor here.

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?

The description is two short sentences, front-loaded with the core action and output, then immediately provides relevant cross-references. Every clause is informative and there is no repetition.

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 a 4-parameter read-only tool with 75% schema coverage and no output schema, the description covers what is compared, the caching behaviour, and related tools. It is nearly complete for an agent's needs, though a hint about response format (markdown vs. json) or typical error cases could add marginal value.

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 75%, so the schema already documents parameters fairly well, including the required 'context' instruction and the UUID fields. The description does not add format or syntax details beyond naming the two fragrance inputs implicitly, so baseline 3 is appropriate.

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 ('Compare') and resource ('two fragrances'), and enumerates exactly what aspects are compared (shared vs. distinct notes/accords/families, scores, audience, AI-synthesised summary). It explicitly names sibling tools (`fragrance_get`, `fragrance_similar`) and contrasts its role, making it easy to distinguish.

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 'See also' line routes the agent to `fragrance_get` for full profiles and `fragrance_similar` for alternatives, which clarifies when to choose this tool. However, it does not state explicit when-not-to-use conditions or prerequisites such as needing valid UUIDs with prior lookup.

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