List Submissions Awaiting Grading

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

Annotations already mark the tool read-only and non-destructive, but the description adds substantial behavioral context: it explains sorting, the two workflow states, what per-submission details are returned, known limitations (New Quizzes, fill-in-the-blank, per-question detail), and the pseudonymization behavior when CANVAS_PSEUDONYMIZE_STUDENTS is enabled, including a pointer to resolve_pseudonym. This goes well beyond the annotations and fully discloses behavior.

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 well-structured with clear sections (purpose, categories, parameters, limitations). It front-loads the core purpose and then systematically covers each relevant aspect without redundancy. Every sentence adds value, and the length is justified by the complexity of the tool.

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?

The description is complete for an agent to call the tool correctly. It explains the return format (grouped by assignment/quiz with per-submission fields), covers parameter behavior, and lists limitations and pseudonymization caveats. No output schema exists, so the description's outline of return contents is essential and adequately provided. Minor omissions like pagination are not critical for a read-only triage tool.

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 input schema has 100% description coverage, so the baseline is 3. The description adds nuance beyond the schema: it clarifies the interaction of include_quizzes with the New Quizzes caveat, explains the default values and what only_pending_review does in practice, and describes how assignment_ids limits the scan. These extra details elevate it to a 4.

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 opens with a clear, specific statement of the tool's function: 'Lists all submissions in a course that still need a human grade, sorted oldest-waiting first.' It then details two workflow-state categories, which distinguishes it from the sibling list_submissions (which lists all submissions). The verb and resource are unambiguous, and the scope (course_id) is explicit.

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 conveys when to use the tool by framing it as a triage list for grading, and it explicitly notes a key exclusion: New Quizzes may not appear with 'pending_review' here, advising to use SpeedGrader or the New Quizzes interface instead. However, it does not name or contrast sibling tools like list_submissions or grade_submission directly, leaving some room for an agent to infer the best alternative.

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