List Course Submission Files

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

Beyond the readOnlyHint and openWorldHint annotations, the description reveals crucial behavior: results are capped by max_files, truncated signals a shortened result set, URLs are time-limited, and pseudonymization behavior changes user_name but not user_id. These details materially affect how the agent interprets results.

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 longer than a simple two-sentence tool, but every sentence adds a distinct operational constraint or clarification (bounding, truncation, URL expiry, pseudonyms). It is front-loaded with the core purpose and then provides necessary edge-case behavior.

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 explaining return fields and semantics. It names the primary output values, explains truncation and time-limited URLs, and covers the pseudonymization edge case. For a tool with six parameters and complex operational behavior, this is highly 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?

Input schema coverage is 100%, so the baseline is 3, but the description adds meaningful meaning beyond the schema: max_files triggers truncation, student_ids should be real Canvas IDs after pseudonym resolution, and the returned file_id is the way to request a fresh URL. This gives the agent guidance on how parameters interact with opaque behaviors.

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 specific verb+resource+scope statement: 'List every file attachment submitted by students across all assignments in a course.' It clarifies this returns a manifest of file entries (filename, file_id, content type, size), clearly distinguishing it from broader submission-listing tools like list_submissions.

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 an explicit use case—bulk-archiving student work before a course expires or teacher account concludes—and points the user toward download_file for fresh URLs at download time. It doesn't explicitly contrast with list_files or list_submissions, but the clear scope and filters make the intended usage evident.

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