canvas_prepare_submission

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known; the description adds genuinely new behavior by enumerating the checks performed (allowed types/extensions, lock, attempts, current submission) and by stating explicitly that nothing is submitted. It does not describe what the check results look like or how failures are surfaced, but the output schema covers returns.

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 short sentences, each earning its place: purpose, negative scope, checks, then the authorization precondition. The most important constraint ('Does not submit') is front-loaded right after the purpose.

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?

With annotations covering safety and an output schema covering returns, the remaining gap is provenance of upload_action_ids — which sibling (likely canvas_prepare_upload) produces the receipts. That missing link is the one thing an agent would still have to guess, so this is nearly but not fully complete.

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%, so the description must carry the parameter burden. It only partially does: 'verified upload receipts' implies upload_action_ids come from a prior upload step, and 'for that assignment' ties assignment_id, but course_id is never explained and there is no hint about the expected id format or ordering constraints.

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 ('Review a file submission') and immediately bounds the scope with 'Does not submit', which separates it from canvas_execute_action. An agent can tell what this tool does without opening the schema.

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?

Clearly frames this as the pre-flight step before a 'separate execute step' and adds a real workflow precondition: 'Obtain user authorization in conversation before the separate execute step.' It stops short of naming canvas_execute_action explicitly or saying what to do when the checks fail, so it is strong but not exhaustive.

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