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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds meaningful context: it records a confirmation, depends on a code, and that changes invalidate the request – that's a non-obvious failure mode. It also discloses an operational constraint (never read mailbox). This goes beyond the annotations without contradicting them, providing useful behavioral insight.

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?

Three sentences with no fluff. The core action is front-loaded, and each sentence adds critical information: what it does, how to get the code (do's/don'ts), and conditions for validity. Efficient and well-structured.

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 4 required parameters (including a nested object), no output schema, and light annotations, the description covers the essential purpose and constraints but omits details like what payloadHash represents, what outputJobId points to, and what 'deterministic blockers' specifically are. It is adequate for a basic call but not fully complete for a complex mutation tool.

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 only 25% (only idempotencyKey has a description). The tool description partially compensates: it explains the 'code' parameter ('the code the reviewer supplies') and implies 'arbitrationRevision' corresponds to the proposed interpretation. However, it does not clarify challengeId or the nested outputJobId/payloadHash structure, leaving significant gaps. The description adds some semantic value but not enough to fully offset the low 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 states a specific verb and resource: 'Record the authenticated reviewer's email confirmation for the exact proposed interpretation.' It clearly identifies the action (recording a confirmation) and the object (a proposed interpretation), and distinguishes this tool from its sibling 'request_control_arbitration' by its confirmatory nature. It is unambiguous and specific, earning a full score.

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 operational guidance: 'Use only the code the reviewer supplies after inspecting the questions. Never read their mailbox or provide their code.' It also conditions validity with 'Changes to the report, source context or draft invalidate the request; deterministic blockers remain.' While it does not explicitly name alternatives (e.g., request_control_arbitration), it clearly implies the confirmation context and provides clear do's and don'ts. The absence of explicit 'when not to use' keeps it from a 5.

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