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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so safety is covered. The description adds a real behavioral constraint absent from the annotations: the full catalogue cannot be listed and a query or filter is mandatory. It does not, however, describe pagination behavior despite a cursor parameter.

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 the purpose and the hard constraint, then a tip, then examples, then see-also routing. Every block is scannable and none is filler.

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 13-parameter read tool with no output schema, the description covers the critical 'you must filter' rule, the ambiguous parameters, and sibling routing. The main omission is any hint about result format or cursor-based pagination.

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 only 46% across 13 parameters, so the description must compensate, and it does for the tricky ones: the dual-nature of q (names OR brands), the brand slug alternative, and worked examples mapping intent to note/minScore/decade/brand. Sort, limit, cursor, concentration, gender, and response_format remain undocumented in prose.

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 'search and filter' plus the resource 'Noteboxd fragrance encyclopedia', and immediately names the sibling tools it is not (fragrance_get, search). An agent can distinguish this from the 25 siblings without opening a schema.

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?

Explicitly states the precondition (query or at least one filter required; catalogue cannot be listed), gives routing rules (use brand slug instead of embedding brand in q), three concrete natural-language-to-parameter examples, and named alternatives for adjacent needs.

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