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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds genuinely new behavioral facts: the call is FREE but rate-limited, and the result includes a 'how sure' confidence measure rather than definitive matches. It stops short of saying what happens on a miss (empty result vs. fuzzy candidate list), which is the one behavior an agent would still want.

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 sentences, front-loaded with the cost/rate-limit signal and the return shape before the input recipes. Every clause carries information - the parenthetical '(not Gmail etc.)' and the quoted query example are both load-bearing rather than filler.

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 10-parameter open-world lookup with no output schema, the description supplies the return fields and the main input patterns, which is the bulk of what matters. The residual gaps are the undocumented `eu_only` and `language` switches and the no-match behavior.

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 only 40% across 10 parameters, so the description has to compensate and largely does: it explains which identifiers are interchangeable (name pair + company/domain, LinkedIn URL, work e-mail, or `query`) and warns that `email` must be a work address, not Gmail. Gaps remain for `name` vs. first_name/last_name, `eu_only`, and `language`, none of which are explained anywhere.

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 and resource ('find a person') and enumerates exactly what comes back: name, job title, company, location, LinkedIn profile, and a certainty signal. It also draws a hard boundary against the sibling enrich_records ('No e-mail or phone in the answer'), so an agent can separate the two without opening a schema.

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 concrete input recipes: first_name + last_name + company (or domain), a LinkedIn URL, a work e-mail, or a natural-language question in `query` with the example 'CFO of Tink in Berlin'. It names the alternative tool explicitly and the condition that selects it (need e-mail/phone -> enrich_records), which is exactly the routing an agent needs.

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