canvas_course_updates

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

No annotations are provided, so the description carries the full burden. It does disclose the key behavioral fact that this tool mutates state by writing notes into the vault, which is more than the name suggests, but it says nothing about whether existing notes are overwritten, whether the write is atomic, what permissions or auth are needed, or how errors mid-write are handled.

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?

It is a single sentence with no filler, which is good, but it compresses two distinct operations (listing and writing) into one clause joined by 'y', so the structure obscures rather than front-loads the side effect. A short split between the read phase and the vault write would cost nothing and help more.

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 mutation tool with no annotations, no output schema, and one undocumented boolean that controls whether the write happens, the description is thin. The one sentence captures the scope but not the side-effect semantics an agent needs before triggering a vault write.

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 only 33% (just 'since' is documented, as 'Fecha ISO'), and the description adds no meaning to any of the three parameters. In particular, nothing explains that dry_run suppresses the vault write or what course_id refers to, leaving the mutation-control parameter undocumented in both schema and prose.

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 names specific resources (announcements, files, modules) and a concrete effect (writes notes into the vault), so the agent can tell it is a read-plus-write course harvesting tool. It does not distinguish itself from close siblings such as canvas_course_inventory, canvas_sync_course, or canvas_export_course_sources, which overlap heavily with 'list and persist course content'.

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?

There is no statement of when to prefer this tool over canvas_sync_course, canvas_course_inventory, or canvas_export_course_sources, and no prerequisites or exclusions. The compound behavior (list AND write) is stated but never explained as a choice the caller is making.

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