canvas_sync

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

With no annotations, the description carries the behavioral burden and mostly does so: it discloses the on-disk target path, the SlideMate-vs-~/CanvasFiles fallback, the background-mode return value {"running": true}, and that existing files are skipped. It omits any authentication prerequisite (a canvas_login sibling exists) and gives no sense of volume or duration for the bulk mode.

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?

Front-loaded with the destination path, then the two modes, then the polling instruction. Three sentences, each earning its place, with no restatement of the tool name or padding.

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?

There is no output schema, but the description supplies the return contract for the async case ({"running": true}) and states the sync case 'returns the result'. For a two-parameter, no-annotation tool this is nearly complete; only the auth prerequisite and the shape of the eventual result are left unstated.

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 coverage is 0%, so the description must compensate and largely does: `course` is described as accepting an id, code, or partial name and as optional (the empty string drives the bulk mode), and the skip-existing behavior is surfaced. It never explains what skip_existing=false does or when a caller would want to override the default.

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?

States a specific verb and resource ('Download course files') plus the exact destination layout and the two operating modes (single course vs. all current courses). It does not explicitly differentiate itself from the sibling canvas_download, which a reader must infer from the phrase 'downloads every file in it'.

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?

Gives an explicit conditional: pass a `course` for a synchronous full download, omit it to fan out across all current courses in the background. It also names the follow-up tool (canvas_sync_status) and tells the agent to poll until a result appears, leaving nothing to inference about the async path.

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