hermes_search

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

With no annotations provided, the description carries the full burden of behavior disclosure. It does this well by revealing three non-obvious behaviors: no-results returns total 0 with empty products (intentionally omitting fallback recommendations), spelling corrections are surfaced in results_for, and page size is fixed at 48. It does not cover authentication, rate limits, or full return format, but for a search tool these quirks are more valuable, so this is strong coverage.

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 four sentences with zero filler. Purpose is front-loaded, and each subsequent sentence covers a distinct behavioral quirk (no-results, spelling correction, page size) that an agent needs to know. Every sentence earns its place.

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?

The tool is moderately complex due to pagination, locale, and no-results edge cases. The description covers no-results behavior, spelling correction, page-size limits, and points to the sibling shape for the return format. It does not explain locale defaults or error/rate-limit behavior, but for a search tool with a 100%-documented schema, this is nearly complete.

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 baseline is 3. The description adds no new parameter-level semantics beyond what the schema already provides; it repeats the fixed page size already documented in the page parameter. The mention of results_for relates to output behavior, not parameter meaning, so it does not elevate the score.

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 opens with a specific verb and resource ('Search the Hermès catalogue') and immediately states it searches by keyword and returns a page of normalized products. It also references the output shape matching hermes-category, which helps distinguish it from category-browsing siblings. This is a clear, non-tautological statement of purpose.

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 description implies usage (keyword search against the catalogue) but never explicitly states when to choose this tool over alternatives like hermes_suggest, hermes_category, or hermes_products. There are no when-not-to-use conditions or direct alternative names. The usage context is clear enough by inference, but lacks explicit routing guidance.

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