people_search

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

No annotations are provided, so the description carries the full burden. It discloses that provider API charges are billed directly to the provider account, which is a key behavioral trait. It also mentions the return fields (outcome, normalized output, raw provider data, _meta.tried), giving insight into the response. However, it does not elaborate on error handling, rate limits, or what happens when the waterfall stops (only implied in the schema). The statement about billing is valuable and specific.

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?

The description is moderately concise, two sentences plus a billing note, but it is dense and front-loaded with the core purpose. It mentions return payload fields and billing behavior, which are useful. There is no wasted verbiage, though the billing info could be seen as slightly tangential but is important for user awareness. The structure is good; the core purpose comes first.

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?

Given the tool's complexity (13 params, no required ones) and the presence of an output schema (not shown here, but indicated), the description covers the essential behavioral and selection aspects. It explains the input modes, vendor control, waterfall behavior (via parameter note), and cost implication. It does not detail return format since output schema exists. It is complete enough for an agent to invoke correctly, though some nuances like exact vendor selection logic are left to the agent.

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 all 13 parameters have descriptions. The tool description adds context that goes beyond the schema: it explains that 'keywords' is 'the SUBSTANCE of most briefs' and explains how providers without keyword fields are ranked. It also explains the purpose of 'limit' as 'the price dial on per-row vendors'. This adds meaningful semantic guidance that the bare schema descriptions lack, so the description compensates well despite the schema's heavy lifting.

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 clearly states the tool's purpose: finding people from a description (role, company, place) or from a source that names them. It distinguishes the tool's broad capability and explicitly mentions vendor pinning and return payload fields, making it distinct from siblings like people_enrich (which likely enriches known people) and people_identity_resolve (which resolves identities). The verb 'search' is implied by the name and context, and the resource is 'people', with specific input modes.

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 description provides clear guidance on what inputs to use ('a role, a company, a place' or 'a source that names them'), and how to control provider ('Use vendor to pin a provider'). It also hints at the 'waterfall' behavior implicitly via the parameter description, but does not explicitly contrast with siblings or state when not to use it. However, it gives enough context for the agent to choose it over enrichment/resolution tools, though it could mention alternatives for known people (e.g., people_contact_find).

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