knowledge_search

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral details: 'No answer generation' clarifies the output is raw retrieval only, and 'raw upstream values, not normalized relevance' warns that scores are not calibrated. This goes beyond the annotations without contradicting them.

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 compact—two sentences—with the core purpose and ordering front-loaded. Each sentence conveys necessary information without padding. The key behavioral caveats ('No answer generation' and raw scores) are placed immediately after the purpose, making it easy to scan.

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?

Given 3 parameters, no output schema, and a non-trivial search tool, the description covers purpose, behavior, and one parameter nuance. It omits the meaning of top_k, default count limits, and the exact structure of returned fragments. While it mentions scores/distances, it does not fully specify the output shape. This is adequate but not comprehensive.

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 0%, so the description must carry the meaning. It precisely explains the semantics of knowledge_ids (omitted vs empty), which is non-obvious and valuable. However, it does not clarify the query parameter (obvious) or top_k (what it controls, default behavior). Since it covers only one of three parameters in depth, it partially compensates but leaves gaps.

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 clearly states the verb 'Retrieve' and the resource 'fragments', and specifies the ordering ('rank order'). It also differentiates itself from answer-generation tools via 'No answer generation', which helps distinguish it from siblings like rag_search. However, it does not explicitly name any sibling tool, so it stops short of a 5.

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 provides concrete guidance for the knowledge_ids parameter (omitted vs empty array), which tells the agent how to restrict the search scope. It does not, however, offer explicit guidance on when to prefer this tool over alternatives like rag_search or knowledge_get. The differentiation is implied ('No answer generation') but not stated as a usage rule.

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