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

The description adds substantial behavioral context beyond the annotations: it explains that confirmation is required, that financial edits may reset approval, that unknown fields and invalid currencies are refused, and that the response includes an exact preview plus a five-minute confirmation token. These details go well beyond the readOnly, idempotent, and non-destructive hints already present.

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 concise sentences, front-loaded with the core action and safety profile. Every sentence contributes useful information: what it does, confirmation requirement, validation behavior, and return value. There is no filler.

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 preview-only tool with no output schema, the description covers the key behavioral contract: it returns a preview and token, requires confirmation, and does not mutate state. The main gap is that the nested input fields are not described at all, but the schema itself provides field structure and types, making the description mostly complete for correct invocation.

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%, so the description must compensate for the lack of parameter documentation. It only says 'saved invoice header fields' and mentions that invalid currencies are refused; it does not identify any of the many nested fields (e.g., tax, fees, due_date, vendor_name) or explain how to specify them. The single 'input' parameter wraps a complex object whose semantics are left to the raw schema.

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 uses a specific verb and resource: 'Prepare a bounded change to saved invoice header fields.' It also explicitly states the return ('exact preview and a five-minute confirmation token') and clarifies that it 'does not apply the change,' cleanly distinguishing it from the sibling edit_invoice_fields tool.

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?

The description clearly establishes the preview context: it requires confirmation, returns a token, and does not apply the change. It also notes that financial edits may reset approval and that unknown fields or invalid currencies are refused. However, it does not explicitly name the alternative tool (edit_invoice_fields) or state when to use that instead, leaving the sibling routing slightly implicit.

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