find

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

Annotations are absent, so the description carries the full burden — and it meets it by disclosing the read-only safety profile head-on ('Read-only: never writes'). It also reveals behavioral nuance beyond the schema: dual retrievers fused via RRF, dense+sparse hybrid behavior for embedding-capable adapters, and provenance attached to results. It stops short of edge behavior like how the fallback behaves when no adapters or the exact ranking output shape, which keeps it from a 5.

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?

Three sentences, front-loaded with the highest-value facts: read-only safety and search scope come first, and the RRF mechanics are compressed into a single sentence. The only waste is the closing 'never writes', which repeats the opening 'Read-only' — a small redundancy that costs a point.

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 tool with no output schema and no annotations, it covers the essentials: what gets searched, how ranking works, what comes back (provenance), and a pointer on interpreting the explain field tied to the RRF equation. It is missing only a bit of extra detail about result shape and edge behavior to be fully self-sufficient.

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%, and the schema already documents limit, query, and explain semantics. The description adds no new parameter-level meaning beyond reaffirming query as free-text matched against titles and bodies. Baseline 3 is correct when the schema does the heavy lifting.

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?

Opens with an explicit verb and resource: 'Search the task store by free-text QUERY'. The mechanism (adapter signals plus Core keyword retrieval fused via Reciprocal Rank Fusion) and the return (best-matching items with provenance) further pin down what it does. It also distinguishes itself from the nearest sibling by name (`similar`), so an agent can tell them apart without opening either 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 a concrete usage frame — 'Use this for "what do I have about X"' — that defines the intended query-by-topic scenario. It also states an explicit when-not: 'To find items like a KNOWN item instead, use `similar`.' That direct alternative routing leaves little to inference.

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