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

Annotations only carry destructiveHint=true, which alone is thin for a write tool. The description compensates by disclosing the required write scope and, importantly, that each invocation appends a new comment rather than upserting, which is a real side-effect trait not expressed in annotations.

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 compact clauses, front-loaded with the WRITE marker and operation, followed by the auth requirement, the idempotency caveat, and the endpoint. No filler or repetition of the title.

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 append operation with no output schema, the description covers auth, side effects, and transport endpoint. The only gap is what the call returns (new comment id / created object), which an agent might want for follow-up, but that is minor.

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 order_id (uuid) and content (1-5000 chars) are already fully documented in structured form. The description adds only the path-parameter framing via the endpoint; it offers no extra semantics such as whether content supports markdown or is sanitized.

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 (add a comment to an order) plus the underlying Admin API endpoint POST /v1/admin/orders/{orderId}/comments. The 'WRITE:' prefix immediately separates it from the otherwise read-only sibling set (get_order, list_orders, etc.).

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?

Gives a concrete prerequisite (a key with Write access to Order details) and a non-idempotency warning ('do not repeat a call that succeeded'), which is exactly the guidance an agent needs before retrying. It stops short of naming an alternative or exclusion, though no sibling offers comment creation, so little is missing.

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