search_knowledge

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

Annotations already declare readOnly/idempotent/closed-world, and the description adds real context beyond them: the local index is refreshed on file change, only registered files are searched, results are ordered best-first, and an empty array is returned on no match. That is exactly the behavioral context an agent needs.

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?

Front-loads the core action and return shape, then adds the routing hint and the empty-result contract. No sentence is filler; the density is appropriate for a retrieval tool.

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 an output schema present, the description needn't explain return values, and it still sketches them. Annotations cover safety, the description covers scope, refresh behavior, and the empty case — nothing an agent needs 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 description coverage is 100%, so query, limit, and account_id semantics (including "matched by content, not by file name") are already fully documented in the schema. The description's "most relevant passages, best first" only echoes the limit parameter, so baseline 3 applies.

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 ("Search INSIDE the account's knowledge files"), names the content types searched, and shows the exact return shape [{name, path, excerpt, score}]. It is clearly distinguishable from siblings like read_knowledge_file and search_mail.

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 names when to use it ("for prices, conditions and codes before reading a whole file") and names the alternative (read_knowledge_file) plus the condition that selects it. It also scopes usage to files the user registered.

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