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

Annotations establish the write profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description adds real behavioral detail beyond them: repeat-avoidance of already published questions, settings inheritance from the first class, and the fact that drafts never consume an included assignment slot. It omits auth/permission needs and what the review link implies, so not a 5.

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?

Five tightly packed sentences, all front-loaded around what can be built and the key constraints; no filler. Slightly dense in the first sentence (four source types in one clause), but every sentence carries distinct 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 an 11-parameter tool with deeply nested, polymorphic sections and an output schema present (so return values needn't be re-explained), the description covers the main branches and the notable edge cases (AP Calc variant, shared-course requirement, slot behavior). Remaining gaps are minor given the rich schema.

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?

With 64% schema coverage, the description usefully compensates by mapping semantics onto several parameters: sections content sources, the courseVariant requirement for AP Calculus, class-derived settings, and the skip-already-assigned behavior tied to avoidRepeats. Undocumented params (title, requestId, instructions, availableAt, dueAt) are largely self-evident from their schema descriptions.

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?

States a specific verb and resource ("Builds an assignment draft") and immediately enumerates the four content sources the draft can be composed from (MC units/topics, FRQ/SAQ ids, readings, diagnostic). This clearly separates it from siblings like update_assignment_draft and duplicate_assignment without opening any schema.

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?

Provides conditional context ("AP Calculus drafts require courseVariant or target classes sharing one course", "Settings start from the first class's defaults") but never states when to prefer this tool over update_assignment_draft or duplicate_assignment, nor any when-not conditions. Usage is implied by the create semantics rather than spelled out.

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