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

Goes well beyond the annotations by disclosing the return payload (jobId, uploadId, key, parts), the one-hour URL expiry, the ETag retention requirement, the size ceiling, and the concurrency refusal condition. Nothing here contradicts readOnlyHint=false, idempotentHint=false or destructiveHint=false.

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?

Four dense sentences, front-loaded with the caller restriction and followed by the mechanics; no filler and no restatement of the title. Each clause carries either a constraint, a step, or a destination tool.

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 multi-step upload with no output schema, the description explains the whole flow (initiate → PUT parts → keep ETags → complete) and its preconditions. The one gap is what to do when a part URL expires, given that refreshWorldUploadParts exists as a sibling but is never referenced.

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?

The description supplies the file-size ceiling and format list that map onto fileName/fileSize, and explains what the returned parts mean. However, the required serverId parameter (path.serverId) is never mentioned in the description, and the 8 MiB partCount rule is left entirely to the schema, so compensation for the low coverage is only partial.

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 ('Begins uploading') and resource ('a world archive') with accepted formats and a size cap, so it is immediately distinguishable from startAssetUpload and startModpackUpload. It also names the follow-up tool completeWorldUpload, anchoring the tool in its workflow.

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?

Opens with an explicit when-not constraint ('Only for an assistant that can send the user's file with HTTP PUT, such as a coding agent with a shell'), which rules out the wrong caller. It also names the preconditions ('Refused while another upload, export or restore is pending') and routes to completeWorldUpload after the parts are sent.

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