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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely new context: the per-call result cap of 100, that results are compact, and that a total match count is returned. It does not explain sort order, the default limit of 25, or the offset ceiling.

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 short sentences in a logical order: what it does, what it requires and returns, then the escape hatch. No filler or restatement of the name.

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?

For a 13-parameter search tool with no output schema, the description covers result shape (compact rows plus total count), the hard precondition, and the pagination alternative. The gaps are pagination mechanics (offset vs the 100-result cap) and how the boolean filters change results, which an agent may need to reason about.

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 62%, with meaningful descriptions on city, near, category, postcode, radius_km and min_confidence, but limit, offset and the require_* flags are bare. The description compensates only indirectly by implying a 100-row ceiling and a location-or-name constraint; it says nothing about what require_email/phone/website do or how offset pages interact with the cap.

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 (search), resource (US businesses and places) and the three axes it searches on (category, name, location). The US scoping and the explicit contrast with export_leads make it unmistakable among 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?

Gives a clear precondition (at least one location filter or a name) and an explicit alternative for the deep-pagination case (export_leads). It doesn't say when to prefer get_place or that category ids must come from find_categories, so it stops just short of a complete routing guide.

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