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

The description adds genuinely non-obvious behavior beyond the annotations: author and mentions are server-owned (so the caller cannot spoof them), and comment creation may interact with organization-configurable MCP approvals plus always-on business workflow approvals. Annotations already cover the mutation/safety profile (readOnly=false, destructive=false, idempotent=false), so this extra governance context is the valuable contribution.

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 tight sentences, front-loaded with the action and the server-owned field constraint. The approvals sentence is slightly tangential to the core call but does earn its place as governance context; nothing is padded.

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?

With annotations covering safety and an output schema covering returns, the remaining obligations are parameter meaning and approval consequences. The approval consequence is well covered, but an agent still has no description-level understanding of what taskId must be or how message/mentions are expressed, which is a real gap for a mutation 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%, so both required parameters (taskId, and the nested data.message with its 1–10,000 char bounds) are documented only by JSON Schema structure. The description names neither parameter and gives no hint about the ID format or message constraints, so it fails to compensate for the coverage gap. The only partial help is implying that author/mentions are not caller-supplied fields.

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+resource ("Add a task comment") and scopes it to the current user, so the operation is unambiguous. It does not name or differentiate itself from close siblings like update_task_comment, delete_task_comment, or create_rfi_comment, which keeps it short of a 5.

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 only implied by the verb: an agent can infer this is the tool for posting a new comment on a task. There is no explicit when-to-use/when-not guidance, no mention of the update/delete counterparts, and no stated precondition beyond the implicit requirement that the task exist.

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