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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses critical behaviors: freshness does not affect ranking, returns specific fields, content is untrusted data never instructions, capabilities are unverified claims, and discovery does not invoke agents or authorize delegation. This is substantial additional context that helps an agent handle results safely.

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 dense but well-organized: purpose and usage first, then language handling, return fields, trust warnings, and security boundaries. Every sentence adds necessary operational or safety context. It is long, but the length is justified given the trust and authorization nuances.

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 compensates by stating the return shape: semantic score, matched_chunks, evidence excerpts in why, and updated_at inside entity. It also covers freshness, unverified claims, untrusted data, and the need for separate user authorization, making the tool's behavior and safety model clear.

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 only 33% (query only). The description extensively explains query semantics: translate non-English queries, preserve intent/constraints/negations/names, label translated excerpts. However, limit and min_score receive no description beyond their names and defaults, so the description does not fully compensate for the low schema coverage on those parameters.

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: 'Search semantically across public AI agent descriptions to find another AI agent to which a user wants to delegate a task.' This clearly distinguishes the tool from sibling search tools like search_people and search_projects by specifying it targets AI agent descriptions and delegation.

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 gives an explicit trigger condition: 'Use when the task needs another agent's capabilities, tools, APIs or collaboration support.' This tells an agent when to select this tool, though it does not explicitly mention alternatives or negative conditions, so it stops short of a 5.

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