Discussions

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that results include unread counts, a useful output trait. It omits ordering, pagination/truncation, and whether announcements or closed topics are included, which matters for interpreting results.

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 short sentences with the core purpose front-loaded, followed by a clarifying example. Slight redundancy between the parameter sentence and the schema, and the example uses 'open' in a way the tool doesn't literally support, but nothing is bloated.

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 one-parameter read tool with no output schema, the description covers what it returns (topics plus unread counts) and how to supply the argument. Only result shape details like pagination or ordering are missing, which is a minor gap.

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 100% and the single parameter is fully documented, including the pointer to get_my_courses for resolving names. The description largely restates the schema ('course_id as the Canvas course ID or as the course name') without adding format or edge-case detail, so the baseline 3 applies.

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 concrete resource and scope: 'Discussion topics for one Canvas course, with unread counts.' An agent immediately knows this returns discussion data for a single course. It doesn't name a sibling it differs from (e.g. get_announcements), but no sibling plausibly overlaps so the differentiation cost is low.

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?

Usage is implied through the example question rather than stated as a rule. There is no when-not guidance and no mention of how this relates to get_announcements, which in Canvas is closely related content. The example does anchor the intended invocation reasonably well.

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