search_knowledge

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is settled. The description adds genuinely non-structured behavior: results are paginated, source-backed, and matched literally rather than semantically, which warns the agent off natural-language queries. It omits ranking/relevance behavior and what happens when nothing matches.

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?

Three short sentences, front-loaded with capability, then results shape, then the alternative tool, then a caveat. 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 4-parameter search tool with a full annotation set and no output schema, this covers capability, likely result shape (paginated, source-backed), and the escalation path. The remaining gap is per-parameter guidance, especially the kind filter, which leaves a little inference to the agent.

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 0%, so the description carries the burden. It explains the query parameter well (literal words, IDs, framework mappings) and hints at pagination, but says nothing about the kind enum (risk/control/all), limit bounds, or offset semantics. Partial compensation 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 (find) and resource (DASF risks and controls) plus the matching mode (literal words, IDs, source framework mapping), which sharply distinguishes this from detail-fetching siblings. An agent can tell what this does without opening the 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?

Explicitly routes to get_risk/get_control for details, which is the key boundary an agent needs. The note about translating natural-language terms to source English clarifies the search mode. It does not address other siblings (scope_risks, investigate_risk, explain_finding), so the routing picture is only partially covered.

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