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

Annotations already establish readOnlyHint and openWorldHint, so the description needn't restate safety. It adds valuable behavioral context: results are descriptive only, return specific fields, outbound links must be preserved verbatim, and sort is mechanical rather than evaluative. This goes well beyond the annotations.

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?

Three tight sentences, front-loaded with the tool's core purpose followed by result semantics and usage cautions. Every sentence earns its place with no redundancy or 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 search tool with no output schema and many optional filters, the description usefully enumerates return fields (prices, availability, $/round, observation time, provenance) and key behaviors. It could be more complete about pagination behavior or default pageSize, but the important selection and invocation context is present.

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?

The description adds semantic value to the sort parameter by emphasizing it is 'a mechanical ordering, never a judgement.' However, with 11 parameters and only 55% schema coverage, the description does not compensate for undocumented params like page, pageSize, brand, roundCountMin, or roundCountMax; most burden still falls on self-explanatory names or the schema.

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'), a specific resource ('canonical ammunition products'), and the key output ('current per-retailer offers'). This clearly differentiates from siblings like get_product (single product), list_calibers/list_retailers (reference lists), and get_market_snapshot (aggregated view).

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?

Provides clear context: this is the tool for searching ammunition products and their offers. It adds explicit behavioral instructions ('Use each offer's outUrl for outbound links (do not rewrite it)') and cautions that results contain no verdicts or recommendations, though it does not explicitly name alternative tools or exclusion conditions.

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