canvas_course_submissions

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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world operation, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the default is a compact row-per-assignment view, while full:true produces a large response including teacher comments and rubric assessments — a real cost/size tradeoff an agent cannot see in the 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 output shape is front-loaded in the first clause, then the escalation path, then the alternative tool — a sensible order with no filler. The field enumeration is long but each item is load-bearing since there is no output schema.

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 no output schema, the description carries the burden of describing return values, and it does so concretely by listing the columns plus the assignment-group weights and drop rules. It could go slightly further on pagination and on how this differs from neighbouring grade tools, but nothing essential for a correct call 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?

Schema description coverage is 100%, so the baseline is 3. The description restates what full:true does but adds no guidance for the raw or page parameters (pagination behavior, when to follow next_page), so it does not meaningfully exceed the schema's own documentation.

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 names a specific verb+resource combination ('Your grades in one course, one compact row per assignment') and enumerates the exact fields returned, then adds the secondary payload (assignment groups with weights and drop rules). It also differentiates itself from the sibling canvas_submission by scoping itself to a whole course rather than one assignment.

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?

It gives clear conditional guidance: use full:true when comments, rubric assessments and every field are needed, and use canvas_submission to read a single assignment's feedback. It does not distinguish this tool from other grade-adjacent siblings such as canvas_missing_submissions or canvas_assignments, so it stops short of full when/when-not coverage.

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