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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds real context the annotations lack: the return payload is an exact preview plus a five-minute confirmation token, and a correction is recorded. That token lifetime detail is behaviorally important and not derivable from structured fields.

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 short sentences, all front-loaded with the action and the non-application guarantee. 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?

With no output schema, the description correctly explains what comes back (exact preview and a time-limited token) and that no mutation occurs. The remaining gap is field-level meaning for the nested line-item payload, which is fully undocumented.

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 input nests a LineFields object with six undocumented properties (quantity, unit_price, total, tax_amount, description, is_verified). The description's phrase 'with supplied values' adds no semantic meaning about any of them, so it fails to compensate for the coverage 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?

The description states a specific verb and resource ('Prepare one explicit new invoice line') and clarifies it returns a preview rather than applying the change, which separates it from the mutating add_invoice_line_item sibling. It stops short of naming that sibling explicitly, so an agent must infer the pairing.

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?

'Requires confirmation' and 'it does not apply the change' signal the workflow context: call this first, then confirm. The five-minute token expiry is a useful usage constraint. It does not name which tool to call afterward to confirm, leaving the next step to inference.

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