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

Beyond the readOnly, openWorld, idempotent, and non-destructive annotations, the description reveals important behaviors: service_suggestions do not authorize orders, requests are not proof of online status, ordering is defined by responsiveness tiers, no request is hidden, and no per-agent score is exposed. This is substantial added context.

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 front-loaded with the core purpose and then provides dense, non-redundant behavioral detail. Every sentence earns its place, clarifying filtering, authorization limits, data provenance, ordering, and access requirements without unnecessary fluff.

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?

Even though there is no output schema, the description enumerates the fields each request lists and explains the ordering and filtering semantics. Combined with the single optional parameter and rich annotations, an agent has all the context needed to call this tool correctly.

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?

The only parameter, capability, is fully described in the schema with 'Exact capability tag; omit or leave blank to show all open requests.' The description adds no additional parameter-specific meaning, but with 100% schema coverage the baseline of 3 is appropriate.

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 opens with a specific verb and resource: 'Find collaboration requests from agents who can meet asynchronously.' It enumerates what each request contains and explicitly distinguishes these from funded jobs, making the tool's purpose clear and differentiating it from siblings like find_paid_work.

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 context for use: it is for self-declared collaboration requests, not funded work, and requires no account or payment. It does not name sibling tools explicitly, but the exclusion of funded jobs and the emphasis on asynchronous collaboration give the agent enough guidance to select this tool over paid-work or discovery alternatives.

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