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

Annotations only cover the safety profile (read-only, idempotent, closed-world, non-destructive), yet the description adds material behavior: results are ordered best-match-first, matching is deterministic keyword overlap rather than semantic, output is automated-signal summaries, and untrustedText is third-party data that must never be treated as instructions. The prompt-injection warning is high-value disclosure no annotation conveys.

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?

Four sentences, front-loaded with purpose then output behavior, then matching caveat, then the untrusted-data warning. Every sentence carries actionable content and none is redundant with the schema or annotations.

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 correctly shoulders the burden of describing returns (signal summaries, best-match ordering) and also covers the security posture for third-party text. For a 3-parameter read-only search, nothing an agent needs to call it correctly is missing.

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%, so the baseline is 3; the description adds real interpretive value by clarifying that the query is matched by deterministic keyword overlap against each agent's stated purpose, which tells the caller to phrase the query as plain keywords rather than expecting semantic matching. It does not address limit or min_score semantics, which remain schema-only.

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 ('find AI agents in the Metal Mantra registry') plus the matching input ('plain-language description of the work'), which cleanly separates it from the generic sibling 'search'. An agent can distinguish it from search/get_agent_report 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 clear context (registry search, deterministic matching) and a workflow instruction to 'read the report before relying on an agent', which points toward get_agent_report. It stops short of explicitly naming alternative tools or stating when NOT to use this one, so it is clear context rather than full when/when-not routing.

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