List Assignment Overrides

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

Annotations already declare readOnlyHint: true and openWorldHint: true. The description adds moderate detail beyond this: it returns overrides targeting students/sections/groups and mentions the 422 error behavior. However, it does not elaborate on pagination, response structure, or any error conditions beyond the 422. It meets the baseline by not contradicting annotations and adds just enough context to be useful.

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?

Three short sentences deliver the purpose, return types, and a key use case. Every sentence carries weight: the first defines, the second specifies scope, and the third explains why you'd use it. There is no redundant language, and the structure is front-loaded with the most important information.

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 read-only list operation with only two simple parameters, the description covers the essential aspects: what it lists, what it returns, and a practical application (auditing before creation). It does not mention pagination or response format, which could be relevant for a large dataset, but given the simplicity and the openWorldHint annotation, the description is sufficiently complete for an AI agent to decide 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?

Schema coverage is 100% with both parameters documented as 'Canvas course ID' and 'Canvas assignment ID.' The description does not add any additional detail about parameter formats or relationships; it simply uses the context of calling overrides for an assignment. Since the schema already covers the parameters, the description correctly relies on it without duplicating information, resulting in a baseline 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?

The description uses a specific verb and resource ('List all due-date / availability overrides for a specific assignment in a course') which clearly identifies what the tool does. It distinguishes itself from sibling tools like 'create_assignment_override' by focusing on listing existing overrides, and it enumerates the types of overrides (students, sections, groups), making the purpose unmistakable.

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?

It provides a practical use case: 'Useful for auditing before creating a new override — Canvas returns a 422 if a student-set override already exists for the same students on the same assignment.' This gives clear context for when to call this tool (before creating an override) and implies an alternative (not using it leads to errors). It lacks an explicit comparison to a specific alternative tool but effectively communicates when to use it.

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