agent_output_verification

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

With no annotations, the description carries the full burden and does so well: it discloses the review-only relay verdict, that human review is required, that no verdict is permission to relay, and the explicit non-capabilities (no factual truth verification, no source fetching, no authorization). This is meaningful behavioral context beyond any structured field.

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?

Front-loads the selection directive ('Choose this to...') and each sentence contributes (scope, alternative, input contract, return shape, constraints). Slightly dense with multiple clauses, but 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?

For a nested-object input with no output schema, the description usefully enumerates the return contents (relay verdict, per-claim findings, orphaned references, owner actions). It defers the full nested contract to evidence-audit.schema.json, which is reasonable but leaves a small gap an agent must close via get_schema.

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 description restates the field set (claims, evidence records, optional unsupported_claims) and points to evidence-audit.schema.json, but the input schema already documents these and directs the agent to get_schema('evidence_audit'), so the description adds only marginal meaning.

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: reviewing an existing AI answer's claims and supplied source excerpts, scoped as review-only. It explicitly distinguishes itself from the sibling pre_action_check ('For action routing choose pre_action_check'), so an agent can route correctly 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 an explicit when-to-use ('review an existing AI answer's claims... without checking a specific intended action') and names the alternative tool for the contrasting case ('For action routing choose pre_action_check'). It also states exclusions ('does not verify factual truth, fetch or validate cited sources, or authorize an action'), leaving nothing to inference.

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