canvas_files

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile needs no restating. The description goes beyond them by disclosing that results are limited to 'accessible' resources (permission-scoped) and that returned file metadata includes download links, which is meaningful because no output schema exists. It omits pagination/raw-mode behavior, which is left to the schema.

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 short sentences, front-loaded with the action and scope, with the return-value note placed second where it belongs. Nothing is superfluous; a little more precision on search vs. plain listing would have made it tighter still.

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 five-parameter read-only listing tool with no output schema, the description covers purpose, scope, and the shape of returned metadata. Pagination and raw-mode semantics live entirely in the schema, which is acceptable given full coverage, though a one-line note on paging would have closed the remaining gap.

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 every parameter (raw, page, context_id, search_term, context_type) is already documented in the schema. The description's scope list loosely mirrors the context_type enum and adds no format or behavioral detail beyond it, so the baseline of 3 applies.

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 uses a clear verb pair ('list or search') against a specific resource ('files') and enumerates the scopes covered (personal, course, group, folder). It does not name the closest siblings such as canvas_file (single file), canvas_find_files, or canvas_folder, so an agent must still infer which file-listing tool to pick, but the purpose itself is unambiguous.

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?

'List or search' implies two modes, but the description never states when to use this tool versus canvas_find_files, canvas_folders, or canvas_file, nor any preconditions (e.g., that context_type and context_id must be paired). No when-not guidance or explicit alternative is offered.

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