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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description doesn't need to re-state safety. It adds real context the annotations cannot convey: that partial parts are discarded and that the server's current world is untouched, which reassures the agent the action is scoped.

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 tight sentences: effect first, then the non-effect clarification, then the precondition. Nothing is redundant or padded.

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 destructive, idempotent cancel operation with no output schema, the description covers the effect, the non-effect on the live world, and the timing constraint. It could say what happens if called after completion (error vs no-op), but nothing essential is missing.

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?

Top-level parameters (body, path) carry no description, matching the 0% coverage signal, and the description adds no parameter detail. However, the nested schema thoroughly documents key, uploadId, jobId and serverId with provenance ('from startWorldUpload', 'from listServers'), so the practical gap is modest.

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 and resource ('Cancels an unfinished world upload') with explicit effect ('discards the parts uploaded so far'). The scoping clause distinguishes it from completeWorldUpload and the similarly named abortAssetUploads/abortModpackUpload without needing the schemas.

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 an explicit precondition ('Only before completeWorldUpload'), which routes the agent away from the complete path and implies the valid window of use. It lacks an explicit 'use abortAssetUploads for assets' style disambiguation, but the world-upload scope plus the precondition cover the main selection decision.

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