delete_review_commentDelete a review comment from a code review. If it's the only message in its thread, the thread is also removed. Only comments authored by this tool can be deleted.
Delete one message. If it was the only message in its thread, the thread goes with it. As with editing, an agent can only delete messages written by its own tool.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Changes observed during successful MCP inspections.
v0.1.17Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry destructiveHint=true and readOnlyHint=false, so the description adds value by disclosing the thread-cascade behavior and the self-authored-message restriction. These details are not available in the structured metadata and are essential for a destructive operation.
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 two tight sentences with the primary action and the most consequential side effect front-loaded. There is no filler, repetition, or irrelevant detail.
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 one-parameter destructive tool, the description covers the core action, a key side effect, and the permission restriction, which is enough to invoke it safely. It does not specify behavior when a message has replies, but that level of detail is not clearly necessary for this simple 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 0%, and the description does not explain what `id` refers to or how to obtain it; the agent must infer that it is the comment/message ID. Because the schema provides no parameter description, the description should have compensated but did not.
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 leads with a clear verb-resource pair, 'Delete one message,' and the tool name/title specify that the target is a review comment. This distinguishes it from comment-related siblings like update_review_comment and resolve_review_comment.
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 provides a relevant permission constraint: an agent can only delete messages written by its own tool-twitter. However, it does not explicitly state when deletion should be chosen over alternatives like resolve_review_comment or update_review_comment; usage is mostly implied by the tool name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.