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

Annotations already establish read-only safety, but the description adds real behavioral context beyond them: the privacy guarantee that author name, photo and profile are never stored, the cost of 1 credit, and the silent-empty-result edge case when the matched Google place does not match the domain. That mismatch behavior is exactly the kind of hidden trait an agent needs.

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 returned data, followed by privacy, fallback and cost. Nothing is padded, though 'Read-only' mildly restates an existing annotation and could be dropped.

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 carries the burden of describing returns and does so concretely (rating, count, themes, quotes). Privacy, cost and the mismatch edge case are covered; only the absence of guidance on result volume or empty-result behavior for a well-matched place is a minor 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 coverage is 100%, so the baseline is 3. The description goes further by explaining the rationale for business_name (the domain-to-place mismatch case), turning an optional string into a meaningful recovery parameter. City, brand and country semantics are left entirely to 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?

The description names the exact resource and return payload: rating, review count, themes and short quotes from public Google reviews. That is specific enough to separate it from every sibling (ads, backlinks, SERP, teardown), though the verb 'get/retrieve' is only implied rather than stated.

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?

It gives one concrete conditional instruction — if the Google place found does not match the domain, reviews are not returned, so pass business_name — which is genuinely actionable. However, there is no guidance on when to choose this tool over siblings or when reviews are not the right signal, so usage is only implied.

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