canvas_create_discussion

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

With no annotations, the description carries the full behavioral burden and does well: it declares the write/mutation nature, the unpublished default, the notification side effect of publishing, and defaults for threaded/pinned. It omits permission requirements and whether an existing topic can be overwritten, so it is strong but not exhaustive.

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 purpose and the mutation warning are front-loaded in the first two lines, and the args list is compact with no filler sentences. The bulleted arg block is a little listy, but every entry adds meaning rather than repeating the schema titles.

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 7-parameter mutating tool with an output schema already covering returns, the description supplies the missing pieces an agent needs: default publish state, notification side effect, and per-parameter semantics. Only auth/permission expectations and failure behavior are absent, which is a minor gap given the output schema exists.

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 compensate, and it does: all seven parameters are explained with semantics beyond the schema, including 'message: prompt body (HTML allowed)', the default-off published flag, and 'course_id: numeric course id; defaults to CANVAS_DEFAULT_COURSE_ID'. Defaults and behavioral effects of each toggle (require_initial_post, threaded, pinned) are clarified.

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 ('Create a discussion topic') and immediately flags the mutation with 'MUTATES the course', which is more than a restatement of the name. It does not explicitly contrast itself with neighbors like canvas_create_page or canvas_post_announcement, so sibling differentiation is only implied by the resource noun.

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 explains the intended workflow context clearly: 'Defaults to UNPUBLISHED so you can review it before students see it' tells the agent this is the draft-then-publish path, and it warns that publishing notifies students. It gives no explicit when-not or named alternative tool, so it lands at clear-context without exclusions.

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