People Search

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

Annotations only declare destructiveHint=true, idempotentHint=false and openWorldHint=true; the description adds the entire economic and temporal contract the agent needs: reserves count times per-person price (reserved_cost_usd), pays only for delivered people, a per-search minimum, free when nothing is found, refund of the unused reservation, a 1-5 minute background runtime, and immediate task_id return. This is substantially beyond what annotations convey.

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?

Front-loaded with purpose, then billing, then async workflow, then filters - a sensible order. It is dense but nearly every sentence carries operational weight; the trailing filter enumeration is the only part that echoes the schema rather than adding information.

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 complex, costly, asynchronous 16-parameter tool with no output schema, the description covers everything an agent needs: what a result contains (fit score, why they matched, audience, public contacts and links), the billing model, the task_id, how to poll, how to cancel, and how to avoid double charging. No material gap remains.

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% and each parameter description already states its platform applicability, so the description's per-platform filter lists (x: min_followers... etc.) largely restate structured data. The consolidated view is mildly convenient but adds no new semantics, so the baseline 3 applies.

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 ('Start a paid job...find people on X, YouTube, LinkedIn, or TikTok who match a plain-language description') and immediately disambiguates it from the sibling status/control/tasks tools by naming them. An agent can distinguish it from people-search-status and people-search-control without opening any 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 explicit workflow guidance: poll people-search-status with the task_id, use people-search-control to pause/resume/cancel, and 'Do not start the same search twice; send idempotency_key so a retry returns the first task instead of charging again.' Both the when-to-use and the when-not-to-use (duplicate starts) are covered.

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