Explain Grade

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

The description adds substantial behavioral context beyond the readOnlyHint/openWorldHint annotations: it discloses that Canvas REST API does not expose curves/fudge points, that a caveat is added for discrepancies over 0.5 pp, that only one student is computed per call, and that reconciliation is against the cross-period grade under grading periods. This goes well beyond the structured annotations.

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 description is structured with a dense first sentence followed by a focused limitations list. Every sentence adds relevant information—calculation details, use case, student constraint, API limitation, grading-period handling, and pseudonym prerequisite. No filler or redundancy.

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?

Despite lacking an output schema, the description thoroughly conveys what the tool computes and what caveats apply. It covers the calculation inputs, the reconciliation behavior, limitations due to API gaps, grading periods, and pseudonymization. This is sufficient for an agent to decide when and how to invoke the tool correctly.

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%, so the baseline is 3, but the description adds useful extra semantics: 'V1 computes one student per call' clarifies the student_id limitation, and the pseudonym-resolution note adds operational behavior around the parameter. The assignment_group_id narrowing behavior is already fully described in the schema, so the description's additional value is moderate but meaningful.

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 and resource: 'Recomputes and explains the weighted course grade for a student.' It enumerates the exact outputs (assignment-group weights, drop rules, per-group breakdowns, letter grade, reconciliation check), clearly distinguishing this from generic grading or policy tools like project_grade and explain_grading_policy.

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 explicitly states when to use the tool: 'Use this when you need to verify that Canvas's displayed grade matches the rules, or to explain to a student or instructor how their grade was calculated.' It also provides important prerequisites and limitations (one student per call, pseudonym resolution, grading-period caveat), though it does not explicitly name alternatives or say when not to use it.

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