find_evidence

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

Annotations are absent, so the description carries full behavioral burden. It does disclose that output is compact, ranked, and budget-limited, but it does not explain ranking criteria, possible failure modes, or what form the evidence takes. This is more than a tautology but still leaves meaningful behavior undocumented.

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 a single tightly written sentence. It front-loads the action and outcome and contains no filler or redundant restatement of the tool name.

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 simple two-parameter tool, the description captures the core contract, but with no output schema it leaves the exact return shape and ranking semantics underspecified. Given siblings like get_evidence_packet, more explicit output expectations would improve completeness.

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 the baseline is 3. The prose reinforces both 'claim' and 'token budget' but adds no new parameter semantics beyond what the schema already states, such as allowed max_tokens values.

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 names a specific verb ('Retrieve'), a resource ('supporting evidence for a claim'), and the output style ('compact, ranked'). The 'strict token budget' further distinguishes it from sibling tools like get_evidence_packet or verify_claim, making the tool's role clear.

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?

The phrase 'under a strict token budget' implies a budget-constrained evidence-retrieval use case, but there is no explicit guidance on when to prefer this over siblings such as verify_claim or get_evidence_packet. No alternatives or exclusions are mentioned.

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