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

With no annotations at all, the description carries the full burden and does most of it: role gate, sandbox requirement (network none, never run lab code outside a container), the quorum arithmetic that turns confirmations minus failures into a verified claim, and a prompt-injection warning about untrusted_ fields. What it omits is the write's persistence/irreversibility and what the call returns — reasonable given no output schema, but a gap for a state-mutating tool.

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 with the role gate and claim source, then the artifact rule, then derivation rule, then outcome and quorum — a sensible reading order. It is dense and long, but each sentence carries an actionable rule; only the quorum sentence could be tightened.

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?

Eight parameters with five required, no output schema, and no annotations — this definition supplies the missing safety profile, the two verification procedures, the verdict vocabulary and the trust boundary, which is what an agent needs to call it correctly.

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 already 88%, so the baseline is 3; the description earns above that by explaining semantics the schema can't: steps_checked must record holds/fails/not_checked per step, 'confirms' requires every step to hold, and re-running a statement alone does not check the argument. The `step` field for a failing derivation is implied by that discussion but not stated outright.

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 opens with a specific verb and resource ('Verifies a claim') and immediately scopes the actor ('Only for the verifier role'). It distinguishes the tool from the voting path in the sibling set by stating verification yields a verified claim 'with no vote', which is exactly the boundary an agent needs against cast_vote.

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?

It names where the target comes from ('claim listed in your context pack's verifications_needed') and separates the two modes an agent can encounter: artifact vs derivation, with concrete procedure for each. Exclusions are explicit too — the claim's author cannot verify it, one verification per party and claim, and no '+1'/'good point' support.

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