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

Annotations report destructiveHint=false and readOnlyHint=falsearen't set, which is the correct neutral baseline for an upload operation. The description goes beyond annotations by disclosing the 50 MB size limit, the password/digital-signature restriction, and the critical truncation risk that silently corrupts files. It doesn't detail failure modes or return error behavior, but the warning about truncation is a meaningful behavioral disclosure for a file upload tool.

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?

Well-structured with numbered paths in priority orderressing the most important guidance upfront)Skip. Each sentence has a clear purpose: what the tool returns, which path to prefer, the caveat on base64, size limit, and password/signature restriction. No filler.

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?

For an upload tool with no output schema and zero required params, the description covers return value (fileId), usage paths, integration with sibling tools, limits, and corruption warnings. The only gap is explicit error behavior on failure (e.g., if uploadId is expired, what error occurs), but the description is otherwise thorough for its complexity.

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%: all four parameters (url, file, fileName, uploadId) have descriptions. The description's three-path guidance adds ordering and selection semantics that the schema alone doesn't convey, which is valuable. However, most of that value is parameter-level guidance, and the description doesn't add much beyond what the schema already documents for each parameter. Baseline 3 with modest increment withheld because the schema already covers descriptions; the added value is in sequencing, not new semantic depth.

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 uploads a PDF to Formify and returns a fileId, with an explicit link to downstream use with create_document or create_draft. It lists three distinct input paths with precedence, making the tool's purpose and scope unambiguous and distinguishable from its siblings.

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?

Provides explicit when-to-use guidance: URL first, then uploadId, then base64 file. It names the sibling tool request_file_upload_url and explains the exact sequence (call it, run curl, pass uploadId). It also gives a clear exclusion rule: avoid base64 unless you can guarantee completeness. This is exemplary usage guidance.

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