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

Goes well beyond the annotations: caps results at 20 identities, warns that coverage is incomplete, notes inclusion of labelled historical roles and interpretations, and clarifies it is not a live provider search and does not authorize outreach. This is exactly the extra behavioral context a read-only search needs.

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-loads the purpose before the caveats, and each sentence adds a distinct constraint rather than restating. Dense but every clause carries information; nothing is 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 two-parameter search tool with no output schema, the description covers result cardinality, coverage limitations, and data provenance. It stops short of describing pagination or the exact shape of a result record, but those are minor for a 20-item capped search.

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 50% (query is undocumented in the schema), and the description compensates by explaining that query targets a company, professional role, or explicitly stated accelerator cohort. workspaceId is fully documented in the schema itself, so the loop is closed.

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 (Search) and the kinds of things searched over (company, professional role, accelerator cohort) and explicitly distinguishes itself from a live provider search, which helps separate it from siblings like find_people. It never names a sibling directly, but the 'not a live provider search' contrast makes its niche legible.

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 exclusions (not live provider search, does not expose other customers' data, does not authorize outreach) and a usage instruction ('Check source dates before recommending someone'). No alternative tool is named, so routing to the right sibling still requires inference, but the context is clear.

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