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

Adds real behavior beyond the annotations: a five-minute token expiry, the exact-preview return, the note that it does not itself bypass accounting export safeguards, and the authority/validation gates. These are precisely the traits an agent needs (time-bounded artifact, no side effect, gated preconditions) and they are consistent with readOnlyHint=true and destructiveHint=false.

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 tight sentences, each doing distinct work: what it does, what it requires, what it returns and does not do. The non-mutation disclaimer is front-loaded where the agent will see it.

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?

With no output schema, the description correctly fills the gap by naming the return values (exact preview + five-minute token) and the safety boundary. It stops short of explaining what the token is used for downstream or what the preview payload contains, which would fully close the loop for a preview/apply pair.

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 0% and the description says nothing about the single `input` object's fields. The schema conveys invoice_id as a required UUID but leaves `notes` (nullable, 10k chars) unexplained, and the description does nothing to compensate for that gap.

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 ('Prepare approval of one reviewed invoice') and immediately clarifies the boundary: 'this returns an exact preview and a five-minute confirmation token; it does not apply the change.' That single clause separates it from the sibling approve_invoice without the agent needing to open either schema.

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 concrete preconditions for use — confirmation, current approval authority, no blocking validation errors, cleared approval workflows — which is more than most preview tools offer. However, it never names approve_invoice or states the two-step sequence explicitly (preview here, then apply with the returned token), leaving the routing to inference.

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