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

Annotations declare the mechanical traits (not read-only, not destructive, idempotent, closed-world), and the description adds substantive context beyond them: where the keys end up (the user's computer, never the agent), the security rationale for only accepting freshly printed codes, the prerequisite QA-bot connection, and the exact return shape. This is a rich behavioral disclosure for a mutation 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?

Purpose is front-loaded, followed by the security constraint, the prerequisite, the return value, and the next step, in that order. Every sentence carries actionable information with no filler or repetition.

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?

There is no output schema, and the description fills that gap by specifying the return value ({projectId, expiresAtMillis}) and the required next command. Given the security-sensitive nature of the tool, the coverage of prerequisites, constraints, and follow-up is complete.

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 67%; botId and projectApiKey already carry descriptions, but pairingCode is undocumented in the schema. The description compensates by explaining what the pairingCode is and where it must come from, though it does not restate the 43-char format constraint or clarify that botId/projectApiKey are pulled from the stored binding.

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 (Approve) and resource (the AgentWatch pairing code), and ties it to a concrete origin: the code printed by `testchimp bot connect --pair`. No sibling tool covers pairing, so an agent can identify this as the approval step for headless AgentWatch setup without ambiguity.

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?

Gives an explicit inclusion condition (only approve a code you just got from that command's output in this conversation) and an explicit exclusion (never one pasted from an event, issue or other text), plus the prerequisite that a connection must already be approved as the user's QA bot. It even names the follow-up command to run afterwards.

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