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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds meaningful context beyond that: 'owner-bound confirmation preview', 'Publication remains unchanged', and a hard precondition ('With no classes, anyoneWithLink must be true'). It does not cover preview expiry or error/rejection behavior, so not a full 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?

Three dense sentences with the core action front-loaded and the required precondition placed last. No filler, though the middle sentences are packed with multiple clauses each.

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 prepare/confirm-style tool with 6 params and an output schema (so return values need no prose), the description covers the workflow position, the immutability guarantee, and the empty-classes constraint. Minor gaps remain around what the preview token/preview represents for the follow-up call.

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 67%, and the description adds semantics not in the schema: the time-zone purpose ('shows their local times'), the result-visibility and student-facing-change scope, and the conditional rule tying anyoneWithLink to an empty classes list. This meaningfully extends the structured fields.

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+resource ('Creates an owner-bound confirmation preview for publishing a draft or republishing') and makes clear it is the preview step rather than the publish itself, which distinguishes it from the sibling confirm_publish_assignment. An agent can identify the tool without opening the 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?

Gives clear context for when to use it (publishing a draft or republishing with new dates) and states that execution requires approval of this specific preview, implying the confirm step. It stops short of explicitly naming the confirm_publish_assignment alternative, so routing is left partly to inference.

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