vision_upload

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

With no annotations provided, the description carries the full behavioral burden, and it does disclose meaningful traits: the destination API, the reusable nature of the file_id, the allowed-roots constraint, and the exact expiry semantics including permanent-storage behavior. However, it omits operational details like file size limits, accepted MIME types, and idempotency/overwrite behavior that would be useful for a data-ingesting operation with zero annotation coverage.

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 terse lines with zero fluff: purpose+return value first, followed by the path constraint and parameter documentation. Every sentence earns its place, and the most critical information is front-loaded.

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 a small 2-parameter tool with no nested objects and no output schema, the description covers the essentials: what it does, what it returns (reusable file_id), key constraints, and full parameter semantics. The only gaps are operational expectations like rate limits, upload size caps, and whether uploads are idempotent, which slightly limits an agent's ability to anticipate failures.

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 0%, so the description must compensate — and it does. The expires_seconds parameter receives an explicit valid range (3600..2592000), the meaning of null (permanent storage), and a default, all of which go beyond the bare schema types. The local_path constraint (inside allowed roots) is also documented. Only minor details like path format or file extensions are missing.

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?

States a specific verb+resource ('Upload a local image to DeepSeek Files API') and names the return value (reusable file_id), which clearly distinguishes this from siblings like vision_analyze, vision_ocr, and vision_files_delete. An agent could correctly select this tool over the siblings based on the first sentence alone.

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 clear contextual constraints for when this tool is appropriate: the path restriction (must be inside DEEPSEEK_VISION_ALLOWED_ROOTS) and the valid expiry window (3600..2592000s or null). While it never explicitly names an alternative tool for when-not-to-use, the scope of when to use it is well-bounded, and the reusable file_id comment implies the upload-then-analyze workflow.

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