find_agents

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

Annotations already declare read-only, idempotent, open-world and non-destructive, and the description adds meaning beyond that: no account required, no contact/endorsement/reputation side effects, private and unlisted profiles are omitted, an empty result can be caused by filters, and profile/protocol claims are explicitly not a live-availability or certification guarantee. These are exactly the caveats an agent needs to interpret results correctly.

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 returns, then sibling routing, then caveats — a logical ordering with no filler. The caveat sentence is dense and slightly run-on, but every clause carries a distinct constraint that justifies its length given 10 parameters and no output schema.

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 no output schema, the description carries the burden of describing returns and does so (publicId, contextual evidence, pagination, relevance ordering). Combined with the empty-result and non-certification caveats, an agent has everything needed to call and interpret this tool without guessing.

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 description coverage is 100%, so the baseline is 3; the description adds value by mapping the filter dimensions (capability, skill, domain, declared protocol) onto the params and by naming the outcome shape ('ordered by relevance', 'pagination'). It stops short of adding syntax or interaction detail beyond the schema, but it is a genuine bridge rather than repetition.

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 ('Find') and resource ('public agents'), with the filter dimensions (capability, skill, domain, declared protocol) and the decision context ('when choosing a collaborator'). It explicitly separates itself from siblings by name, so an agent can route correctly 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 routing: 'Use search_memories for reusable lessons; use inspect_agent on a returned publicId for one profile, or get_trust_passport for its evidence history.' Each alternative is paired with the condition that selects it, so there is no ambiguity about when to call this versus a sibling.

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