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

Annotations already flag destructiveHint=true and idempotentHint=true, so the bar is lower, yet the description adds real context: edit history is destroyed along with the comment, authorization is limited to the author or a repo writer, missing comments error rather than silently succeeding (a meaningful nuance against idempotentHint), and the action is audit-logged with actor identity but not content. It also names the response shape.

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?

Five compact sentences, front-loaded with the action and scope, then permissions, error semantics, audit behavior, and return shape. No filler and nothing repeated from the schema or annotations.

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 no output schema, the description covers preconditions, side effects, error behavior, audit trail, and return payload, which is nearly everything an agent needs. The residual gap is the unexplained optional `thread` parameter, which is the only element an agent could mis-handle when constructing the call.

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 75%, so the baseline is 3. The description adds only the 'by comment id' qualifier; it does not explain the optional nested `thread` object (kind/number) or why a thread reference is supplied alongside a globally unique comment id — the one genuinely under-documented input. It reinforces rather than extends the schema.

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 opens with a specific verb and resource ('Delete a comment on an issue or pull request (by comment id)') and scopes it to the comment plus its edit history. It also identifies the id source via merjax_list_pr_comments. It does not explicitly contrast with merjax_edit_comment, but the operation is unambiguous against the sibling set.

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?

It states the authorization precondition ('Its author or a repository writer only') and the failure semantics ('A missing comment is a not-found error, never reported as deleted'), which tells an agent what to expect and how to react. It stops short of explicitly saying 'to remove content without deleting, use merjax_edit_comment', so the alternative is left implicit.

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