find_evidence

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

With no annotations, the description carries the full burden. It usefully discloses the scoring method and the shape of each hit (exact text, page, surrounding context), but never states that it is a read-only operation with no side effects, nor whether it reads from disk/network or has any cost.

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?

Two tight sentences with no filler; the purpose is front-loaded and the actionable instruction is last. Every clause carries information.

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?

No output schema exists, and the description compensates by describing the return fields (text, page, surrounding context) and how to use them. Nothing critical is missing for a 1-required-parameter evidence search, though a note on the claim_id/query relationship and read-only nature would make it 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 coverage is 80%, so the schema already documents key, query, claim_id and include_references. The description adds no parameter-level meaning beyond that (it mentions 'the claim' generically), so the 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 ('Rank the source's sentences') and the relevance criterion ('by relevance to the claim'), plus the retrieval method (BM25 + number matching). An agent knows exactly what this returns, though it does not explicitly contrast itself with siblings like verify_quote or read_source.

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?

Usage is implied rather than stated: the closing instruction 'copy quotes verbatim from here' tells the agent this is the quote-sourcing step, but there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. read_source for full text, verify_quote to check a quote).

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