find

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

No annotations are present, so the description carries the disclosure burden. It adds substantive behavioral context by explaining the hybrid vector similarity + BM25 search with Reciprocal Rank Fusion and its recall benefit. It does not explicitly describe data scope or side effects, but as a search tool this is reasonably transparent.

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 front-loaded with the most important usage guidance, followed by a one-sentence algorithmic note, then a clean Args block. Every line adds actionable information with no 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?

The description covers the full parameter surface, the retrieval mechanism, and usage context, and an output schema exists so return behavior need not be restated. The only minor gap is that it never explicitly names the exact corpus being searched, though collection, agent_handle, and memory_type strongly imply it.

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?

The input schema has 0% description coverage, and the description fully compensates by explaining all eight parameters. It adds concrete details like the default/max for limit, example filters for source_format, agent_handle, and memory_type, and the meaning of each filter.

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 what the tool does: find is for retrieving meaning via hybrid vector/BM25 search, distinct from grep for symbol/value lookups and from WebSearch/WebFetch for external research. It names a specific role and differentiates it from alternatives.

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 opens with explicit routing guidance: use find before WebSearch/WebFetch for research, use it before answering why/how/what-did-we-decide questions, and prefer grep for symbol/value lookups. This tells the agent exactly when to choose this tool over alternatives.

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