upload_reference

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

With no annotations, the description carries the full burden and does well: it discloses the 50 MB cap, that base64 is only practical for small files because every byte is written out, that the HTTPS link needs no token but expires, and that it returns an SSH push command or a local folder otherwise. The one behavioral trait not covered is what the 'overwrite' flag does when the target file already exists.

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?

Front-loaded with the destination and file types before the operational details, and every sentence adds information. The prose is somewhat dense and parenthesis-heavy, but nothing is redundant.

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?

Covers both the inline-data path and the out-of-band copy paths in enough detail for an agent to act and to relay instructions to the user; the output schema handles return structure. The missing piece is overwrite semantics for an existing reference file.

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. It explains 'part' and 'filename' implicitly through the path template and covers 'data_base64' thoroughly (whole file, base64, 50 MB limit), but the 'overwrite' parameter is never mentioned, leaving one of four params undocumented anywhere.

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 (upload) plus the exact destination ('parts/<part>/ref/<filename>') and the two artifact classes it handles (STL/3MF/STEP models vs PNG/JPEG/TIFF/BMP scans). It also distinguishes itself from siblings by naming trace_outline as the consumer of image uploads and describe_model as the follow-up step.

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?

Gives clear context for each mode: upload a model to remix it, upload an image to trace it with trace_outline, and notes the part folder may not exist yet. It routes the agent to the next step (describe_model) but does not explicitly exclude sibling write paths like write_part or save_version.

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