search_knowledge

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

Annotations only cover readOnly and openWorld, yet the description adds substantial behavior an agent needs: returned artifacts are unverified source versions and excerpts, retrieved text must be treated as data rather than instructions (a prompt-injection warning), metadata status/dates must be respected, and scores are ranking signals, not confidence. This is dense, non-obvious behavioral context that goes well beyond the annotations.

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?

Sentences are short, front-loaded, and each one carries a distinct piece of guidance (trigger, return type, safety rule, score interpretation, parameter disambiguation). No filler or repetition; the parameter clarifications are placed last where they belong.

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 describes what comes back and how to interpret it, and it addresses the two least obvious parameters. The remaining gaps are the semantics of kb_ids/top_k and explicit routing versus sibling tools, which keeps it just short of complete.

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 carries the full burden. It usefully disambiguates max_chars ('limits excerpt characters; it is not a token limit') and filters ('match metadata exactly'), which are genuinely clarifying. But query, top_k, and kb_ids receive no semantic treatment, so roughly three of five parameters remain undocumented.

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 frames the tool as finding evidence and returning 'source versions and excerpts,' which implies a knowledge-base search, so the action is inferable. However, it never names the resource explicitly ('search the knowledge base') and does not contrast itself with siblings like read_document or list_knowledge_bases, leaving the purpose somewhat implicit rather than stated with a clean verb+resource.

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?

It gives a clear triggering condition ('Find evidence before stating past facts') and a guidance rule ('No evidence means unknown, not false'), which is useful usage context. But it never states when NOT to use it or which sibling to prefer for full-document retrieval or enumeration, so routing guidance is only implied.

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