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

Annotations only cover read-only and closed-world, so the description carries the return-value burden and does so: open/closed status with dated evidence, a source-agreed phone, an action recommendation, two extra "may_have_missed" businesses when need is supplied, and the not-found behavior ("reported as not in Truvon"). "how to act" stays vague, and there is no note on latency, cost, or what happens when no identifier is supplied.

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 long, comma-spliced sentences pack real information but read as a run-on, with the triggering condition and the input recipe competing for the front position. Phrases like "how to act" and "One not found is reported as not in Truvon" assume brand knowledge without glossing it.

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 8 parameters, zero required, no output schema and only 63% schema coverage, the description should resolve which inputs are mandatory or how partial input is treated, and it does not. It adequately covers the added value of need and the 10-item cap, but an agent cannot tell from this text what a minimal valid call looks like.

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?

At 63% schema coverage the description meaningfully compensates: it states the accepted identifier combination ("name plus phone, website or address, and the town") and explains what the need parameter unlocks, which the schema only partly conveys. It does not clarify zip vs place precedence or how sole-argument calls (e.g. website only) are handled.

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?

"Check up to 10 businesses you found elsewhere (maps, web, a link)" gives a specific verb (check), a bounded resource (businesses), and a scope that implicitly separates it from discovery siblings like find_local_businesses. The name-plus-title synergy makes the verification role unmistakable, though no sibling is named explicitly.

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?

"before you give your user a phone or send them somewhere" is a concrete trigger condition, and "Send the name plus phone, website or address, and the town" tells the agent what input to assemble. It stops short of naming alternatives (get_business_record, find_local_businesses) or saying when not to call it.

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