Upload file by URL

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

Annotations only declare readOnlyHint=false and openWorldHint=true, and the description goes well beyond them: it discloses idempotent behaviour ('if the same URL already exists, Printful returns the existing file'), the asynchronous status lifecycle (waiting → ok or failed), and a hard input-rejection rule for deprecated .ai/.psd/.tiff sources. Those are exactly the mutation traits an agent needs before calling.

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, zero preamble. The core action is front-loaded, followed by the dedup, async, and rejection details in descending order of importance. Every sentence carries information an agent would otherwise have to guess.

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 description covers the write behaviour thoroughly, but there is no output schema and the description never says what comes back — presumably a file record with an id and the status field it just mentioned, which an agent needs in order to poll or reuse the file. For a 4-parameter mutation with no output schema, that return-shape gap leaves the definition short of complete.

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?

With 50% schema description coverage, the schema already documents `type` and `visible`, but `url` and `filename` have none. The description adds meaning only for the URL (it identifies the remote source and is the dedup key), while `filename` and the interaction between the two name sources go unaddressed. Partially compensates for the coverage gap, but not fully.

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 opens with a specific verb and resource: 'Add a file to the Printful file library by URL.' No sibling tool in the list touches files, so there is no ambiguity with list_orders, create_mockup_task, or any other sibling. An agent can tell exactly what this tool does from the first sentence.

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?

'By URL' implies the usage condition (no direct binary upload; the file must already be reachable at a URI), and the dedup sentence hints at a valid retry path. But there is no explicit when-to-use, no when-not-to-use, and no pointer to a follow-up tool for checking the async status it describes. Guidance is implied rather than stated.

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