canvas_outline

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real value beyond that: it warns that inline items may be incomplete and explains the follow-up call needed to get complete data via the per-module paginated endpoint.

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 tight sentences with the primary purpose front-loaded and the pagination caveat immediately after. The completion-marking-UI clause is slightly cryptic but earns its place as an exclusion.

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 needn't be described, and annotations cover safety behavior. The key behavioral gap an agent would hit (incomplete inline items) is disclosed, leaving only minor gaps like course_id semantics.

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. It explains module_id well (selects one module's items, triggers the paginated endpoint) but leaves course_id entirely undocumented beyond its name. Partial compensation merits a mid score.

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: 'List modules, or all items in one module,' which is clearly distinct from sibling tools like canvas_courses or canvas_assignments. It doesn't explicitly name the sibling it replaces, but the resource scope 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?

Gives a clear when-not ('do not navigate completion-marking UI URLs') and a procedural disambiguation: call again with module_id to reach the paginated items endpoint. No sibling alternative is named explicitly, keeping it below a 5.

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