Create New Quiz

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

Annotations (openWorldHint: true, destructiveHint: true) already signal side effects and external integration. The description adds the 'LTI' context, which substantiates the openWorldHint, and the modern-vs-classic engine positioning is useful. However, it doesn't address behavior beyond the schema/annotations such as idempotency, failure modes, or publishing effects. Reasonable value added over annotations, but nothing striking.

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 zero waste. The first sentence front-loads the action and scoping; the second sentence handles differentiation and points to the alternative. Every word contributes value - exemplary economy of language.

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 create operation with 8 params (2 required), 100% schema coverage, no enums, and annotations signaling side effects, the description covers the essentials: what it creates, where, and how it differs from the sibling create_quiz. Gaps: no mention of what the tool returns on success (no output schema exists to clarify), nor idempotency semantics - especially relevant given destructiveHint: true. Adequate but not comprehensive for an agent deciding whether to call this vs. understanding consequences.

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 100%, so the baseline is 3. The free-text description adds no parameter-specific meaning beyond what the schema documents, but it doesn't need to - the schema already fully documents all 8 parameters. The description's engine distinction (New vs Classic) could theoretically imply different parameter behavior, but that connection isn't made explicit.

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?

Uses a specific verb+resource ('Create a New Quiz (LTI) in a Canvas course'). Explicitly distinguishes itself from the sibling create_quiz by naming the alternative and its use case ('for Classic quizzes use create_quiz'), which is exactly the type of sibling differentiation that merits full marks.

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?

Explicitly names the key alternative (create_quiz) and provides a when-not rule ('for Classic quizzes use create_quiz'). Could be a 5 if it elaborated on when New Quizzes vs Classic is appropriate (e.g., feature requirements), but the primary decision rule for the agent is clear and actionable.

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