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

The description discloses critical behavior beyond the annotations: rows are hash-chained under the API key, verdicts cannot be edited or removed after resolution, and the tool returns the row hash and sequence number. The annotations only indicate non-read-only, non-idempotent, non-destructive, so this added context is genuinely valuable and non-contradictory.

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?

The description is front-loaded with the most important timing constraint and each sentence adds meaningful context: what the tool does, how integrity is enforced, when to use it, and what is returned. The motivational sentence about scorecards is slightly extra but reinforces appropriate usage.

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?

Given the absence of an output schema, the description appropriately includes the return value (row hash and sequence number). It covers timing, immutability, keying, and usage expectations. Combined with the rich input schema, the agent has enough information to invoke the tool 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 description coverage is 80%, so the schema already explains most parameters. The description does not add parameter-level detail, but it does clarify the overall concept of a 'verdict' and the honesty mechanism, which helps an agent understand why ca, band, and rule_id are relevant. This matches the baseline for high schema coverage.

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 clearly states the specific action ('Seal a verdict BEFORE the outcome exists') and the resource (a call/verdict), and explains the purpose: enabling later scoring while preventing post-outcome tampering. This distinguishes it from sibling tools like scan, scoreboard, or scorecard without needing to open their schemas.

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 description gives explicit timing guidance ('BEFORE the outcome exists') and strong direction to use this tool for every call, including confident ones. It does not explicitly name alternative tools or exclusion cases, but the context is clear enough that an agent should seal all calls.

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