Create Assignment Override

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

Annotations already provide openWorldHint and destructiveHint; the description enriches this with the 422 conflict behavior, the omit-a-date-to-leave-unchanged semantics, and the pseudonym gotcha. However, given destructiveHint is true, it would be helpful to explain what makes this destructive, and no contradiction exists, just a modest gap.

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?

At roughly 110 words across 6 sentences, the description is dense but every sentence earns its place, covering purpose, constraints, error behavior, and a configuration caveat. It's effectively front-loaded with the core purpose and would only be slightly improved by trimming.

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 9-parameter tool with no output schema, the description covers the critical ground: target selection, date constraints, format, an error case, and an environment-conditional prerequisite. Minor gaps remain — return behavior is unspecified (no output schema note) and the destructiveHint flagged in annotations is unaddressed.

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?

User-schema description coverage is 100%, so the baseline is 3. The description adds meaningful cross-parameter constraints not in the schema: the exact-one-target and at-least-one-date rules, the ISO 8601 format with example, and the 'omit to leave unchanged' date semantics. This goes beyond what the schema states.

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 first sentence, 'Create a due-date / availability override for a specific assignment, targeting a set of students, a course section, or a group,' uses a specific verb+resource and clearly scopes the target types. This distinguishes it from nearby siblings like list_assignment_overrides and set_student_assignment_dates.

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 usage rules: mutual exclusivity ('Exactly one of student_ids, course_section_id, or group_id must be provided'), the required date-field constraint, an explicit alternative ('use list_assignment_overrides to audit first'), and a conditional prerequisite ('If CANVAS_PSEUDONYMIZE_STUDENTS is enabled, call resolve_pseudonym first'). This is exemplary when-to-use guidance.

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