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

With no annotations, the description carries the burden well: it discloses the result shape (snippets and section anchors, not full articles), AND matching semantics ('all query terms must match'), and that a tag disables synonym expansion. It does not cover auth/permissions, result limits, or empty-result behavior, so it stops short of full behavioral coverage.

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?

Purpose is front-loaded in the first sentence and most sentences carry actionable routing or workflow guidance. It runs long (eight sentences) and repeats the tag/synonym behavior already stated in the schema, which is mild redundancy rather than 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 five-parameter, read-style search tool with no annotations and no output schema, the description supplies the return shape, the search-string convention, and the correct follow-up path. Minor gaps remain around limit/default behavior and what happens when nothing matches.

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 baseline is 3; the description still adds meaning by telling the agent how to phrase q ('do not send a full question or split it into speculative keyword searches') and by surfacing the AND-matching consequence of multi-term queries. The tag/expand interaction it mentions is already in the schema, so not all of it is incremental.

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 ('Locate KB articles or source sections') plus the input form ('short topic keywords'). It explicitly distinguishes itself from query_knowledge op=ask and clarifies it returns snippets/anchors rather than full articles, so an agent can separate it from kb_get_document and query_knowledge without opening a 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 explicit when-to-use ('user asks to find written material', 'explanation missing a specific fact'), when-not-to-use ('for general definitions, explanations, comparisons and combination/caution questions, start with query_knowledge op=ask'), and names the alternative. It also bounds the follow-up loop: read one section with kb_get_document only if a fact is still missing, and do not re-search or read every result.

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