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

Annotations already cover read-only/non-destructive/open-world, and the description adds real operational context beyond them: five runs per question on the free plan, 30–90 second latency, and daily-allowance consumption. It does not spell out that results vary between runs (consistent with idempotentHint=false) or what happens when the allowance is exhausted, 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?

Two sentences, front-loaded with what the tool does and its measured outputs, then operational constraints. Dense but every clause carries information; the enumeration of returned metrics is somewhat long but justified since no output schema exists.

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?

With no output schema, the description takes on the burden of explaining return values and does so (rate, average position, range, competing brands, cited domains, report link), plus latency and quota. It stops short of covering failure modes or how the returned report link relates to the get_report/unlock_report siblings.

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%, so the baseline is 3. The description adds light value by stressing 'plain buying questions as a shopper would type them' and implying the models list via 'and/or Gemini', but adds nothing on the domain parameter or default model selection that the schema does not already state.

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 ('Asks ChatGPT, Perplexity, Claude and/or Gemini') against a concrete resource (the user's buyer questions) and names the exact output measured (how often the brand is named). It is clearly distinguishable from siblings like list_checks or get_report, which are retrieval tools rather than measurement runs.

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?

Gives usable invocation guidance: pass one to five plain buying questions phrased as a shopper would type them, and warns that runs take 30–90 seconds and consume the free daily allowance. It does not explicitly say when to prefer a sibling (e.g. get_report for retrieval, unlock_report for full data), so routing guidance is implied rather than stated.

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