canvas_prepare_upload

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this consistently ('writes nothing to Canvas'), then adds non-obvious behavior the annotations cannot convey: payload size ceilings per transport, that a server path is never accepted over HTTP, and that assignment attachments do not constitute a submission. Permission/authentication requirements are the main thing not covered.

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?

Very dense with no filler: the safety claim is front-loaded, then transport constraints, then the domain caveat, then the execution rule. Each sentence carries distinct information; the line-broken phrasing makes it slightly harder to scan than a cleaner sentence structure would.

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?

An output schema exists, so the description correctly avoids explaining return values and instead focuses on the prerequisite behavior (staging vs executing). It is nearly complete for a staging tool, with only the parameter-validity rules (e.g., when course_id/assignment_id are needed for destination='assignment') left to inference.

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 description coverage is 0% across 6 parameters, so the description carries the burden. It does add real meaning for the two ambiguous transport parameters (source_path local-only at 25 MiB, content_base64 HTTP-only at 8 MiB) and hints at destination via the assignment-attachment caveat, but filename, course_id, and assignment_id are never explained, including which are required for the 'assignment' destination.

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?

Uses a specific verb+resource ('Stage immutable upload bytes and return the exact review') plus a scope boundary ('writes nothing to Canvas'), which distinguishes it from the actual-execution sibling canvas_execute_action. The phrase copy is slightly opaque about what the 'review' actually contains, keeping it short of a perfect 5.

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 a concrete conditional rule for the follow-up step ('Execute the returned action only when the user wants this exact upload') and states which parameter to use per transport (local stdio vs base64 over HTTP). It does not explicitly name canvas_execute_action as the next tool, so the routing to the sibling is left implicit.

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