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

Annotations already cover the safety/property profile (readOnly, idempotent, non-destructive, closed-world), so the description adds context on top: A4 page format, the exact page contents, and a real behavioral branch (Free adds a credit line and no logo; Pro renders unbranded with the customer's logo). It also states the return value is a path. It does not address overwriting an existing file at out_path or any tension between 'write' and readOnlyHint (the write is a rendered artifact, not a mutation of the invoice record).

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?

Two dense sentences, front-loaded with the core action and ending with the branding variance, which is the only non-obvious choice. 'Call this tool to' is filler that could be dropped, but overall the text earns its place.

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 2-parameter tool with full schema coverage, annotations, and no output schema, the description covers purpose, output (returned path), page contents, and plan-dependent branding. The remaining gap is overwrite behavior when out_path already exists, which an agent would plausibly want to know before invoking.

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 coverage is 100% and the schema already documents both parameters in detail (including the default path, the .pdf requirement, and page contents). The description adds only that a path is returned, so it does not meaningfully extend parameter meaning beyond the structured fields — baseline 3.

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: write one stored invoice as an A4 PDF and return the path, plus what appears on the page (issuer, BILL TO, dates, items, taxes, totals). The scope ('one stored invoice', returns a path) implicitly separates it from invoice_get/invoice_list, but no sibling is named explicitly, so differentiation still requires inference.

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?

Usage is only implied: 'one stored invoice' signals that the invoice must already exist (schema points to invoice_create), and the Free vs Pro sentence tells the agent what branding to expect. There is no explicit when-to-use/when-not or alternative routing (e.g., use invoice_get for data, this for a file), so an agent must infer the choice.

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