verify_answer

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

With no annotations at all, the description carries the full disclosure burden. It does add real behavioral context — per-claim verdicts, evidence, corrections, and a blocking outcome — which tells the agent this tool can gate its response. It does not say whether the call is stateful, what 'recorded tool outputs' scope means (session? prior calls?), or that it is side-effect free.

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-loaded purpose, then the call trigger, then return behavior, then args — a sensible order with no filler sentences. The Args block is long only because it compensates for 0% schema coverage, so the length earns its place.

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 policy-driven verification gate with an output schema present, the definition covers purpose, timing, and all three parameters with their override semantics. It leaves a gap around prerequisites — whether evidence must first be supplied via record_evidence and how defaults are established by set_policy — which an agent would need to call this confidently.

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% and the schema declares 'strictness' and 'action' as bare strings with no enum, so the description is the only source of meaning. It supplies exactly that: draft is the full answer intended for the user, strictness is lenient|balanced|strict, action is annotate|block|rewrite, plus the key nuance that both are one-off overrides of an existing policy.

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 — 'check every factual claim in a draft answer against recorded tool outputs' — which is unmistakably different from a generic validator. It does not, however, distinguish itself from siblings like verify_claim or rewrite_grounded, so an agent must infer the split between whole-draft verification and single-claim checking.

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?

Provides an explicit trigger: 'Call this before giving the user any answer based on tool results.' That is clear when-to-use guidance. It stops short of naming when-not to call or pointing to alternatives such as verify_claim for single assertions, which keeps it below a 5.

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