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

Annotations carry the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), but the description adds genuinely non-redundant behavior: statelessness, no persistence, and that the timestamp changes on every compilation — which explains and reinforces idempotentHint=false. It also discloses the SHA256 hashing mechanism. It does not state what the returned capsule looks like beyond 'timestamped SHA256', which is minor.

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 tight sentences, front-loaded with the core action and followed by the exclusion list. 'using the production compiler' is the only phrase of questionable weight, but it does distinguish the real compiler from a test one.

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?

No output schema exists, and the description does at least characterize the return as a timestamped SHA256 capsule. But for a tool whose entire input is a six-field structured object with zero schema documentation, the description leaves the semantics of the research state — and of the numeric support/contradiction fields — entirely unexplained.

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?

One nested object parameter with six required subfields and 0% schema description coverage — no property has any description in the schema. The description only frames it as 'caller-supplied research state' and never explains what regime, support, contradiction, or execution mean or what units the numeric fields take, so the agent cannot construct a valid capsule from the description alone.

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 pair: freeze caller-supplied research state into a timestamped SHA256 capsule. The word 'capsule' plus 'compile' separates it from verdict_decide and verdict_review_jury, though no sibling is named 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?

The negative scoping list ('no persistence, Jev call, signature, paid receipt, trade approval or settlement') implicitly tells the agent this is not the signing/settlement path, which is useful routing context. However it never names the alternative tool to use for those operations (presumably verdict_contract or verdict_decide), so the agent must infer the routing.

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