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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description usefully adds what actually happens: status becomes dismissed and the reason is persisted as feedback for Converra learning. It doesn't state reversibility or permission requirements beyond what the schema notes for customerId.

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, front-loaded with the action and effect, with example utterances at the end. The feedback idea is briefly repeated between the first and second sentences, a minor redundancy.

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 destructive mutation with full annotation coverage, no output schema, and three well-documented parameters, the description covers action, effect, and fit. It leaves out reversibility and any post-dismissal behavior, which keeps it from being fully 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 100%, so the baseline is 3; the description goes beyond it by explaining that the reason parameter is stored as feedback used for future optimizations, giving it downstream meaning the schema text only hints at.

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 (reject/dismiss) and resource (pending deployment/PR) plus the resulting state change to 'dismissed'. It is clearly a rejection action, but it does not explicitly distinguish itself from nearby siblings such as decide_approval or request_approval that also touch the approval flow.

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?

Provides concrete trigger phrasings ('reject this PR', 'dismiss this deployment', 'I don't want this change') that map user intent to this tool. It gives no explicit when-not-to-use or named alternative, so it stops short of full routing guidance.

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