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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real behavioral substance on top — it returns an honest empty answer when data is insufficient and never estimates or fills gaps, and it discloses the corpus's content boundaries. No rate limits or latency context, which keeps it below a 5.

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-loaded with the payload (observed benchmarks and the statistics returned), then the guarantees (honest empty answer, no estimation), then the exclusion. Dense but each sentence carries distinct information; the negative-scope sentence is slightly ancillary but defensive and useful.

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 bears the burden of describing returns — it does so precisely (median, p25-p75 band, sample size, currency, scope, and the empty-answer case). Combined with the 100%-covered input schema and read-only annotations, an agent has everything needed to call and interpret it.

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 market, metric, and category are already fully documented in the schema (including the pointer to benchmark_categories). The description adds only the notion that each returned figure carries an exact scope, which is output-side rather than 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?

Specific verb+resource: it returns observed price and assortment benchmarks for a product category, and it names the exact figures returned (median, p25-p75 band, sample size, currency, scope). It also carves out its boundaries by stating what the corpus does NOT hold, which lets an agent separate it from analysis/advice-style siblings.

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?

Clear usage context: query a category for market reference figures, omit filters for aggregates (schema), and an explicit exclusion — do not ask it for conversion rates, revenue, or AOV. It does not restate the sibling routing in the description (benchmark_categories appears only in the schema), so it stops short of full when/when-not/alternatives coverage.

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