delete_comment

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

With no annotations, the description carries full burden. It discloses the irreversible nature, critical authorization constraint (403 otherwise), and implies a side effect of permanent deletion. This is transparent and actionable.

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, all essential. Front-loaded with the core action and key clarification. No wasted words; every sentence earns its place.

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?

The tool is simple, and the description covers core aspects: action, parameter clarification, authorization, irreversibility, and a safety instruction. No output schema exists, but it still feels complete; a minor improvement could be mentioning typical response (e.g., 'Returns 204 No Content on success'), but not required for agent selection.

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%, baseline 3. The description adds crucial disambiguation for the 'id' parameter (NOT issue index, get from list_comments), which goes beyond the schema's simple 'Comment ID'. It does not add much for repo/owner, but the id clarification is significant.

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 it deletes a comment by its id, explicitly distinguishes from issue index, and references list_comments for obtaining the id. This is a specific verb+resource with clear differentiation from siblings like delete_issue.

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 explicit guidance: confirm with user first, notes irreversibility, and states authorization requirements (only author or admin can delete). This helps the agent decide when to use the tool and setting expectations.

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