Set Student Quiz Accommodation

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

The description goes well beyond the annotations (openWorldHint, destructiveHint) by detailing failure tolerance ('Partial failures are tolerated — a failure on one quiz does not abort the rest'), the exact return envelope structure (applied, skipped with skip_reason, failed with error, not_found, summary), and edge-case behavior (quizzes with no time limit are skipped for extra_time but still get extra_attempts). It also explains the pseudonym resolution prerequisite. These are concrete behavioral traits that an agent needs to set expectations and handle results correctly.

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?

Every sentence in the description earns its place. It front-loads the core purpose, then sequentially covers scope, alternatives, timing caveats, performance, failure semantics, return format, and required preconditions. No redundant phrasing or filler; it is information-dense yet readable. The structure naturally guides an agent from deciding to call it, to understanding what it does, to handling its output.

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 complex tool with 6 parameters, no output schema, and fan-out behavior, the description is remarkably complete. It explains the return envelope in detail (applied, skipped, failed, not_found, summary), covers the pseudonym resolution prerequisite, explains the time multiplier calculation and its edge cases, and clarifies the scope of application. An agent would have everything needed to call it correctly and interpret results.

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 schema already documents each parameter. However, the description adds critical semantics not in the schema: the formula for time_multiplier ('extra_minutes = round(quiz.time_limit * (multiplier - 1)), minimum 1 minute'), the skip behavior for quizzes without time limits, and the effect of omitting quiz_ids (target all Classic Quizzes). This goes beyond baseline 3, though it does not fully elaborate on every parameter's edge cases, so a 4 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 precise verb-object pair: 'Apply extra time and/or extra attempts to a specific student across all Classic Quizzes in a course (or a specified subset).' It names the exact resource (student quiz accommodations) and scope, and distinguishes itself from the sibling set_student_new_quiz_accommodation by explicitly stating which quiz types it covers and which it skips. No ambiguity remains about what this tool does.

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?

The description gives explicit when-to-use and when-not-to-use guidance: it states that New Quizzes are skipped and directs the agent to the sibling tool, mentions that assignment due-date overrides are not handled here (separate feature), advises re-running after creating new quizzes, and warns about per-quiz API calls for performance. It also provides a conditional instruction to resolve pseudonyms when CANVAS_PSEUDONYMIZE_STUDENTS is enabled. This is exemplary routing and usage context.

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