get_course_assignment_analytics

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

With no annotations, the description carries the burden of behavioral disclosure. It discloses the lifetime-data limitation, lack of grading_period_id support, and the fallback, which are significant behavioral traits. It doesn't cover permissions or error conditions, but for a read-only analytics endpoint, the key caveats are addressed.

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 sentences plus a note, every clause adds value: metrics, distinction from list_assignments, and lifetime-data caveat with fallback. No filler.

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 analytics tool with no output schema, the description clearly states return content and key limitations. It stops short of describing the exact response structure, but an agent would know what results to expect and when to use it.

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?

The schema already documents course_id fully ('Canvas course ID'), so the description doesn't need to repeat it. The description adds no extra parameter-specific semantics, but given 100% schema coverage, the baseline of 3 is appropriate.

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 opens with a specific verb+resource: 'Get aggregate statistical analytics per assignment' and enumerates exact metrics (min/max/median scores, submission counts). It explicitly distinguishes itself from siblings by noting 'not the assignments themselves' and pointing to list_assignments, which differentiates it clearly.

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?

Provides explicit when-to-use guidance: use this for aggregate statistics rather than assignment details, and explicitly warns that it returns lifetime data and does not support grading_period_id, directing users to list_submissions for semester-scoped data. This is an exemplary alternative-selection statement.

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