hm_search

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

No annotations are present, so the description carries the full behavioral disclosure burden. It goes beyond a simple 'search' statement by describing output contents (pricing, images, colors, per-size stock, search-quality metadata), a spelling-correction feature, and pagination edge-case behavior. The only missing context is lower-level operational detail like rate limits, auth, or data freshness.

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 3 sentences and information-dense. It front-loads the core action, then covers output composition and edge cases. A small amount of redundancy exists between the first sentence and the opening of the second ('Search H&M product listings by free-text keyword' / 'Runs a free-text keyword search'), which prevents a 5.

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?

There is no output schema, so the description compensates by summarizing return contents and search-quality metadata. It also handles the pagination contract and empty-result behavior, which are the most common sources of confusion in search tools. It does not claim a full field-level shape, but it provides enough context for an agent to select and invoke the tool correctly.

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 100%: query, page, and page_size each already have clear descriptions including defaults and ranges. The tool description adds only mild value by framing query as free-text search and noting real page-based pagination, but the schema already covers the essential parameter meaning. 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 names a specific action ('Search'), a resource ('H&M product listings'), and the mechanism (free-text keyword). It also distinguishes this tool from category browsing by explicitly describing that nonsense keywords return zero products instead of a fallback. Among H&M siblings like hm_search_suggestions and hm_categories, an agent can clearly tell what this one does.

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 explicitly contrasts this tool with category browsing, stating when to expect genuine empty results versus fallback sets. It also clarifies real page-based pagination and that out-of-range pages return an empty products array rather than an error. This provides enough when-to-use and when-not-to guidance without naming siblings directly.

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