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

Annotations already declare write, non-destructive, non-idempotent, closed-world, so the safety bar is lower. The description still adds genuinely useful behavior context: the body is markdown with a specific mention format, and the author is derived from the API key rather than supplied. It does not state what is returned or whether duplicate posts are deduplicated.

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?

Two short sentences, purpose front-loaded, followed by two non-redundant details (markdown/mentions and key-bound authorship). No filler and nothing that duplicates the annotations or schema.

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 two-parameter write tool with annotations and no output schema, the definition covers the essentials: what is created, where, in what format, and under whose identity. The one gap is the response — with no output schema, a note on whether the created comment (or its id) is returned would close the loop.

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 only 50% (issueId is documented in-schema with UUID/TEAM-123 rules, body is not). The description compensates by defining body semantics — markdown content plus the @[Nombre](user:UUID) mention syntax — which is exactly the missing half. It doesn't restate issueId resolution, but the schema already handles that.

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?

Specific verb+resource+target: adds a comment to an issue, with the body format and mention syntax spelled out. It clearly contrasts with read-only siblings like list_comments by being a write, but it never names update_comment or delete_comment as the alternatives, so sibling differentiation is only implicit.

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?

Usage is implied by the purpose and by the constraint that authorship is bound to the key's user (so no author can be chosen), but there is no explicit 'use this when' or exclusion versus update_comment/list_comments. The agent must infer that editing an existing comment belongs to update_comment.

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