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

Annotations only indicate this is not read-only and not destructive, so the description adds valuable behavior: temporary server memory, 10-minute expiration, and the no-external-URL constraint. It does not contradict the annotations and meaningfully discloses lifecycle behavior.

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 tight sentences with no filler: purpose, consent precondition, expiration, large-file guidance, and URL restriction are all packed efficiently. Each sentence 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?

The description covers consent, expiry, endpoint preference, and URL restrictions, which is strong for invocation. However, with no output schema and no mention of return values or how the uploaded document is referenced by sibling tools like download_document, an agent is left guessing about post-upload behavior.

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 description coverage is 0%, so the description must compensate for explaining parameters, but it never names or explains base64, extension, or consentToUpload. It indirectly hints that base64 must contain raw document data by rejecting external URLs, but this is insufficient given the complete lack of parameter descriptions in the schema.

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 clearly identifies the action (upload), the resource (document to PaperLumo temporary server memory), and the key precondition (user consent). It also differentiates this tool from siblings like delete_document and download_document by focusing on the upload action and temporary nature.

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 provides clear context: use after user consent, for temporary storage, and not for external URLs. It also gives explicit guidance to prefer the binary /api/mcp/files endpoint for large files, though it does not mention sibling tools as alternatives.

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