canvas_open_url

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

Annotations already declare readOnly/openWorld/non-destructive, but the description adds real behavior: unsupported links are never fetched and the Canvas token is never forwarded, plus an untrusted-data warning against prompt injection from Canvas content. That is meaningful context beyond the annotations. It leaves the effect of the `refresh` parameter and any caching behavior undisclosed.

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 core action, then constraints, then the safety caveat; every sentence carries information. Slightly longer than necessary and the untrusted-data note, while useful, is a policy statement that could be condensed.

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?

An output schema exists, so return values need not be described, and the annotation set covers the safety profile. The remaining gap is the undocumented `refresh` flag, which is material for a tool that may otherwise re-fetch stale content.

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 0%, so the description must carry parameter meaning. It partially covers `url` by enumerating acceptable link types, but gives no format expectations, and the `refresh` boolean is never mentioned or explained anywhere. An agent cannot infer what refreshing does or when to set it.

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 ("Follow a supported Canvas link") and scopes it with the typed navigation allowlist, enumerating the accepted link kinds (course, section, page, assignment, file, quiz, discussion, module). An agent can tell this is a URL-resolution tool rather than a lister or fetcher. It does not explicitly contrast with the sibling canvas_open_item, which appears to overlap in intent.

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 a clear positive condition (same-instance supported links) and a negative one (external/LTI/unsupported links return an explicit state without fetching). It stops short of naming an alternative tool for the unsupported case or stating when canvas_open_item should be preferred instead.

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