get_counterevidence_candidates

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

With no annotations, the description carries the full burden, and it usefully discloses that the tool is non-mutating with respect to confirmed counterevidence and claim verification. It does not cover ordering guarantees, whether calls are idempotent, or what the limiting behavior is.

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 tightly written sentences, front-loaded with the core retrieval action and followed by the crucial non-mutation boundary. No padding or 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?

An output schema exists, so return values need no explanation, and the tool's role is clear. The gap is the entirely undocumented parameter set, which for a 4-param tool with 0% schema coverage leaves invocation details under-specified.

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% across four parameters, and the required run_id, plus claim_id, statement, and limit, are never explained. The phrase 'ranked, topically filtered' hints at the limit and statement fields but adds no real semantics for any of them.

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 (Retrieve) and resource (ranked, topically filtered candidate documents) with the downstream purpose (host contradiction classification). It distinguishes itself from sibling write tools by clarifying that retrieval only registers candidates, though it never names find_counterevidence or submit_counterevidence explicitly.

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 through contrast: the description says it 'never adds confirmed counterevidence or verifies a claim,' steering the agent away from submit_counterevidence and verify_claims. However, it gives no explicit when-to-use trigger or statement of preconditions such as an existing run.

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