List Course Submission Files

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

Annotations only supply readOnlyHint=true and openWorldHint=true, so the description carries the burden of behavioral disclosure and delivers thoroughly: max_files truncation with a truncated flag plus truncation_note explaining the retrieval path, time-limited download URLs with a 1-hour TTL, and the CANVAS_PSEUDONYMIZE_STUDENTS behavior with stable per-course pseudonyms while user_id remains the raw numeric stable key. None of these behaviors are inferable from the structured annotations. No contradiction with readOnlyHint or openWorldHint.

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?

Two dense paragraphs, front-loaded with the core purpose and manifest shape before layering in truncation, expiry, and pseudonymization edge cases. Every sentence earns its place, but the prose is heavier than the calibrated ideal — more numerous clauses per sentence and a few asides could be tightened without losing meaning. Still well-structured and not fluffed.

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 compensates by detailing the manifest contents (original filename, file_id, content type, size), the truncation signal (truncated true, truncation_note available for retrieval instructions), the URL-expiry interaction with download_file, and the pseudonymization edge case. For a 6-parameter tool with 100% schema coverage and an absent output schema, nothing an agent needs to call it correctly or interpret its results 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 schema already documents course_id, max_files semantics (range, default 500), student_ids restriction including the resolve_pseudonym note, assignment_ids, workflow_state enum, and attachments_only. The description adds little parameter-level meaning beyond restating the default and limit — its added value addresses output and behavioral semantics (manifest fields, URL expiry, truncation) rather than the parameters themselves, which warrant no higher score.

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 first sentence names a specific verb and resource ('List every file attachment submitted by students across all assignments in a course') and contrasts it with plain course-file listing by defining a distinct scope: one entry per student-submitted file across all assignments. It also differentiates from the sibling download_file by framing the tool as a manifest producer that returns file_id for later re-fetching. An agent can distinguish this from list_files, list_submissions, and download_file without opening their schemas.

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 gives a concrete trigger scenario ('Useful for bulk-archiving student work before a course expires or a Free-For-Teacher account is concluded') and instructs pairing with the sibling download_file to obtain fresh URLs at download time. It also cross-references resolve_pseudonym for parameter handling under pseudonymization. However, it does not explicitly state when to prefer list_submissions or list_files instead, leaving some when-not-to-use guidance implicit.

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