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

Annotations already carry destructiveHint=true, so the description doesn't need to re-declare risk. It adds useful context the annotations don't: the mutation is a write to the invoice activity log and the underlying call is POST /invoice/{invoiceId}/comment. It still omits who may comment, whether the comment is editable/deletable, and what the response contains.

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?

A single compact sentence with the mutation marker front-loaded, then effect, then endpoint. No filler or 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 simple comment-attach operation with no output schema, the essentials are present, but it does not say whether the created comment is returned, whether userId may be omitted (defaulting to the caller), or any rate/permission constraints. Adequate but with clear gaps.

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 100%, so all three parameters are documented in the schema; the description only restates invoiceId via the URL path template. It adds no meaning beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource ("adds a comment to an invoice") and immediately distinguishes it as a mutation ("WRITE") from the read-heavy siblings like mercoa_get_invoice and mercoa_find_invoices. The parenthetical that the comment lands in the invoice's activity log further pins down what the tool actually produces.

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 "WRITE" marker and the note that the comment appears in the activity log imply when this is appropriate, but there is no explicit guidance on when to use it versus alternatives or any stated prerequisites (e.g., permissions, userId defaults). Usage is inferable rather than stated.

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