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

The description discloses the critical non-obvious contract: the tool reads no reviews and fetches no data itself, and the calling model must run the procedure with its own web search to produce the result. This goes well beyond the annotations (readOnly, idempotent, openWorld=false) and is exactly the kind of execution-model disclosure an agent needs, and it is consistent with those hints.

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 single most important fact (framework, not analysis) followed by the no-data-fetch caveat and then examples. The three examples are longer than strictly necessary but earn their place for a routing-heavy, ambiguous-purpose tool; only minor trimming is possible.

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 an output schema present, the description needn't explain return values, and it correctly spends its budget on the execution contract and realistic invocation scenarios. It leaves unstated what happens when a business has no reviews or how to choose between this and overlapping siblings, a modest gap.

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%, and each parameter already carries its own explanation (city_metro disambiguates same-named businesses, category sets review-volume expectations). The description adds no parameter-level detail beyond the schema, so the baseline 3 is correct.

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 states a precise, unusual deliverable: a research framework (procedure, output schema, quality rubric) for mining public reviews, explicitly NOT the finished analysis. It also names the concrete analytical outputs (complaint taxonomy, theme extraction, sentiment trajectory, differentiators, red flags), so an agent knows exactly what it gets back and how it differs from siblings like business_teardown or local_visibility_audit.

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?

Three concrete example invocations establish when to call it (finding real patterns beyond a star rating, checking rating stability over 90 days, buyer-side diligence on staffing/ownership changes). That is clear usage context, but no explicit exclusions or named alternatives among the sibling tools are given.

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