Get my feedback on an assignment

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds valuable behavioral context by enumerating the return contents (comments, rubric, attempt history) and the 'your submission' scope. It does not repeat annotation flags, and it explains what data is returned beyond the tool name. No contradictions with annotations.

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?

The description is two sentences, front-loading the core functionality and the expected content, followed by a concrete usage example. There is zero fluff, and every sentence earns its place. Perfectly concise for an agent to parse.

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 read-only tool with only two parameters and no output schema, the description adequately conveys what the tool returns (comments, rubric, attempt history) and its scope ('your submission'). It lacks explicit mention of error cases or pagination, but these are minor for such a simple tool. The example query further anchors its use. Overall, sufficient context for correct invocation.

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 schema provides 100% coverage for courseId and assignmentId with descriptions, so the baseline is 3. The description does not add parameter-specific guidance (e.g., format or validation), but it implicitly clarifies that both are required and used to identify the assignment. No additional semantics beyond schema are provided, which is acceptable given full schema coverage.

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?

The description states a specific verb ('get'), resource ('submission feedback'), and scope ('for one assignment'), and clarifies the content (professor's comments, rubric assessment, attempt history). It is clearly distinct from sibling tools like canvas_get_grades or canvas_get_assignment, which serve different purposes.

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?

The description explicitly ties usage to a natural-language query ('what did my professor say / how was I graded?'), giving a clear trigger. It does not name alternative tools or state when not to use it, but the sibling list and the focused example guide the agent well. Slight gap in explicitly excluding other grade-related tools.

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