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

Adds meaningful behavioral and security context beyond the annotations: the deposit is single-use, expires in 10 minutes, allows no reading, is not an account API key, and the returned headers must not be published. This is exactly the kind of context an agent needs.

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 tight sentences, front-loaded with purpose and action, followed by transfer mechanics and a security warning. No filler or redundancy.

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 lifecycle, required computations, transfer mechanics, and security obligations, and it references upload_url and returned headers despite having no output schema. It leaves optional parameters and the follow-up finalize step unmentioned, but the core invocation is fully navigable.

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 0% schema description coverage, the description compensates for the core required parameters: size_bytes and sha256 are tied to 'Compute the size and the SHA-256 of the local PDF', and filename is implied. However, optional parameters like title, language, guest_mode, and notice_version receive no explanation.

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 states a specific action ('Creates a single-use 10-minute deposit') and a concrete workflow (compute size/SHA-256, transfer bytes via PUT), which clearly identifies this as the upload-preparation step and distinguishes it from siblings like foliade_finalize_upload.

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 gives clear procedural context: compute the PDF size and SHA-256, then PUT the bytes to upload_url. It does not explicitly name alternatives or when-not conditions, so it stops short of a 5.

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