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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds billing behavior ('1 point per returned record') that the annotations do not express, which is materially useful; it stops short of describing pagination or ordering behavior.

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?

A single sentence that front-loads the resource and scope, then the returned fields and the cost model. No filler, nothing redundant.

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 correctly names the returned fields (rating, text, author), and both parameters are documented in the schema. Only pagination/ordering semantics and sibling routing are absent, which are minor for a simple two-parameter fetch tool.

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%, including the domain/URL example and the max_items cap with default, so the schema carries the parameter burden. The description's 'by domain or URL' only restates the business parameter and adds no syntax, format, or boundary detail beyond 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+resource ('Get customer reviews for a Trustpilot business') and even enumerates the returned fields (rating, text, author). It does not, however, differentiate itself from siblings like run_trustpilot or run_trustpilot_search, so an agent must infer the split between fetching a business profile, searching businesses, and pulling reviews.

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?

The '1 point per returned record' line implies a cost-aware usage context and the input form (domain or URL) is given, but there is no explicit when-to-use guidance, no mention of when to prefer run_trustpilot_search, and no prerequisites or exclusion conditions.

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