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

Beyond the annotations, it discloses side effects the schema cannot: financial edits may reset approval, the token is single-use against the previewed state, and unknown fields or invalid currencies are refused. These are exactly the behavioral facts an agent needs before a destructive write.

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?

Four dense sentences with no filler, and the refusal and reset-approval warnings are useful. The core purpose sentence sits third rather than first, which slightly hurts front-loading.

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 destructive, confirmation-gated mutation with annotations covering safety, the description covers the preview handshake, token expiry, side effects, and rejected inputs. The only gap is that it never hints what a successful call returns, though no output schema exists to lean on.

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 reported as 0%, so the description must carry the parameter meaning; it does, stating that only the confirmation_token from the matching preview is accepted and that stale tokens fail. It does not add format or length detail, but the operation is single-parameter and the semantic constraint is the important part.

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 names the specific resource (saved invoice header fields) and the exact operation (apply the change produced by preview_edit_invoice_fields), which clearly separates it from the sibling preview tool. The phrasing 'Prepare a bounded change' is slightly at odds with an apply operation and is buried after the token rules, keeping it just 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?

It states the prerequisite explicitly ('only the exact change returned by preview_edit_invoice_fields, after the user confirms that preview') and the invalidation condition ('changed or expired records require a new preview'). An agent knows both when to call it and when not to.

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