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

Annotations already declare this as a destructive, non-readonly, idempotent operation. The description adds meaningful context: approval authority is required, blocking validation errors must be absent, approval workflows must be cleared, and accounting export safeguards are not bypassed.

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 key constraint is front-loaded and most sentences carry useful information. The phrase 'Prepare approval of one reviewed invoice' is slightly redundant after the opening instruction, but overall the definition is compact and readable.

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 single-parameter operation with rich annotations and no output schema, the description covers the essential prerequisites and token lifecycle. It does not describe the response or failure shape, but the annotations and preview flow reduce the need for that detail.

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?

With only one parameter and low schema description coverage, the description compensates well by explaining that only the preview's confirmation_token is accepted and that the token must match the exact confirmed preview. It does not add format details beyond the schema, but it clarifies the token's source and validity constraints.

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 states a specific action: applying the exact change from preview_approve_invoice to approve one reviewed invoice. It clearly distinguishes execution from the preview sibling and anchors the operation to a confirmation token.

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 explicitly says to use this only after the user confirms preview_approve_invoice and only with that preview's confirmation_token. It also states that changed or expired records require a new preview, which is a concrete when-to-use and when-not-to-use rule.

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