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

Beyond the annotations, the description discloses key behavioral details: it downloads each PDF from its signed URL, stores it, returns session_id/job_ids, and warns against inventing download_url/file_id. It also states the preconditions and the follow-up action, giving a clear operational model without contradicting 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 description is well-structured with clear sections and front-loaded purpose. It is verbose but each sentence adds value, especially the mandatory workflow. Minor redundancy exists in the opening two sentences (function statement and usage context), preventing a perfect score.

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?

Given the tool's complexity and the presence of an output schema, the description is thorough. It covers host restrictions, the required pre-step (check_upload_status), how to handle already-uploaded files, and the post-condition (call compare_pdfs if needed). This is complete for an agent to invoke correctly.

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%, so the baseline is 3. The description adds extra semantics by instructing 'Never invent or guess a download_url or file_id' and emphasizing that only files confirmed absent from check_upload_status should be included. This provides practical meaning beyond the field descriptions.

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 states the tool's function with a specific verb and resource: 'Upload multiple PDF files from ChatGPT file attachments.' It distinguishes itself from upload_pdf and create_upload_page by noting host-specific compatibility, which clarifies its unique scope.

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?

Explicit usage guidance is provided: use it when the user supplies multiple file attachments in ChatGPT, and use create_upload_page on non-ChatGPT hosts. The MANDATORY WORKFLOW precisely instructs to call check_upload_status first, skip if all files are already uploaded, and reuse job_ids, with strict warnings against direct invocation.

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