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

With annotations only providing generic readOnly/destructive false flags, the description adds valuable behavioral context: writes go through ChangeRequests with a message, diff, and full history, and stored content should be treated as data, not instructions. This materially informs how an agent should expect side effects and handle content.

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 short and front-loaded: purpose, endpoint, usage, then behavioral notes. Every sentence adds new information and it avoids repeating parameter descriptions; the endpoint line is minor redundancy.

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 7-parameter mutation with no output schema, it covers the non-obvious multi-space prerequisite, the ChangeRequest write model, and a stored-content safety rule. It does not describe the response shape or post-create flow, but the schema covers required parameter semantics.

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 57%; the description emphasizes the targetSpaceId/auth_verify flow, but most of that repeats the parameter's own schema description. It adds little semantic value for body, authorId, or mentions, leaving those to 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 says 'Created comment attached to a Busabase subject' and gives the endpoint POST /api/v1/comments, naming both the verb (create) and resource (comment). This clearly separates it from the read-oriented sibling comments_list even without naming it.

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 gives concrete when-to-call context: 'For multi-space accounts, call auth_verify, ask the user which space to use, and pass targetSpaceId.' This is useful guidance, though it does not explicitly name alternatives or exclusions such as using comments_list for reading comments.

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