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

Beyond the readOnly/idempotent annotations, it discloses the return form (PDF attachment), the non-error failure mode when no invoice exists, and a concrete auth behavior — an unauthenticated call triggers a sign-in prompt on printdash.io. These are exactly the operational traits an agent cannot infer from annotations.

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?

The primary output is front-loaded in the first clause, followed by the conditional case and the auth note. Three sentences, all earning their place, though the aside about the order page's Download button is the least essential.

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 an output schema present, the description needn't detail the response body, and it still covers preconditions, auth, and the empty-result case. It leaves open what happens for an invalid or unknown order number (error vs. 'no invoice'), a minor remaining gap for a single-parameter lookup.

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 explains that the order parameter accepts an order number or the id from its link. The description adds only "for one order," so it neither compensates for nor extends the schema — the baseline 3 applies.

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 names the exact resource ("The tax invoice for one order as a PDF attached to the result") and its success/failure semantics (invoice exists vs. "no invoice yet"). It also implicitly distinguishes itself from get_order by noting the order page link has a Download invoice button, so an agent knows this tool is the programmatic path to the same artifact.

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?

It states the prerequisite condition clearly: the order must be invoiced (paid, or approved on a Team account), and tells what happens when that isn't met. It does not explicitly route the agent to an alternative (e.g., get_order for order details), but the invoicing precondition is a strong usage signal.

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