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

Annotations already indicate readOnlyHint=false, destructiveHint=true, and idempotentHint=true, so the agent knows this is a mutating, idempotent operation. The description adds valuable context: it records email-confirmed authorization (not a legal signature), and that old revisions, changed sources, expired codes, and replays are rejected. This goes beyond what annotations provide and clarifies the safety and validity constraints without contradicting the annotations.

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 three sentences with no wasted words. It front-loads the primary action and then provides critical constraints and context. Each sentence earns its place: the first states what the tool does, the second warns against unethical code acquisition, and the third clarifies rejection conditions and the non-legal nature. It is appropriately sized for the tool's complexity.

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 tool with four required parameters, a nested object, and no output schema, the description covers the essential aspects: the purpose, the code source, rejection conditions, and the non-legal nature. It does not explain the 'challengeId' parameter, which could be a session or challenge identifier, but given the schema also lacks a description, this gap is not entirely the description's fault. Overall, it provides enough context for an agent to understand the tool's role and constraints.

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 description adds meaning to two parameters: 'code' (one-time code supplied by reviewer) and 'revision' (exact revision). However, it does not explain 'challengeId' at all, which remains ambiguous. While it partially compensates for the low coverage, it leaves one parameter unexplained, so it does not fully bridge the gap.

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 action (record confirmation), the object (reviewer's explicit confirmation), and the specific mechanism (one-time code supplied by the reviewer). It also distinguishes this from sibling tools by specifying 'review' and 'this exact revision', which differentiates it from other confirm_* tools like confirm_contribution_review or confirm_document_review.

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 clear context on when to use the tool: after the reviewer inspects the exact revision, and it explicitly prohibits inventing, searching for, or reading the code from the mailbox. It also mentions rejection conditions (old revisions, changed sources, expired codes, replays), which help the agent understand when not to use it. However, it does not explicitly name alternative tools or provide an explicit 'when-not-to-use' statement beyond the rejection criteria.

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