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

Annotations already cover read-only, idempotent and closed-world safety, so the description only needs to add operational context. It usefully discloses that the result is extracted text that may be PDF text, OCR (explicitly marked as such), or SIE, which tells the agent to expect imperfect extraction and to check the OCR marker. Minor gap: no statement about failure when the PDF has no text layer.

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, front-loaded with the resource and the return shape, followed by the API reference. No filler, though the bare URL reference adds little for an agent that will not browse 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?

The output schema exists, so explaining return values is optional, yet the description goes partway by naming the text formats. What is missing is the routing information an agent needs against the many read_*_pdf and get_*_pdf siblings, which is the more valuable gap to close for such a simple tool.

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% for the single parameter, so baseline 3 applies; the description only implicitly maps DocumentNumber into the /orders/{DocumentNumber}/preview path. Note the schema's own description says "identifies the offer", which conflicts with the order framing, but that is a schema issue rather than a description one.

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 order as a PDF. Returns the text for you to read" states a clear resource and outcome, but the sibling list contains both get_order_pdf and read_order_pdf, and the description offers nothing that separates reading extracted text from fetching the PDF itself. An agent cannot pick between them from this text alone.

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?

No when-to-use or when-not-to-use guidance is given. The tool never mentions get_order_pdf, read_offer_pdf, or read_invoice_pdf, so the caller has no stated rule for choosing this over near-identical siblings.

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