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

Annotations already declare readOnly=false and destructive=false; the description adds meaningful context beyond them - that classes reach no one until published, that as_draft keeps them hidden, that the action is reversible via cancel_class, and that it requires a Cotlet API key with app access. It also states the return payload (new class IDs and first dates), which is useful since no output schema exists. No contradiction with the non-destructive hint.

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?

Purpose and the one-off/series distinction are front-loaded, and the remaining sentences (draft visibility, reversibility, return values, auth) each carry distinct information. It is dense but nearly every clause earns its place; only the auth sentence feels slightly tacked on.

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 mutation tool with no output schema, the description covers the key things an agent needs: what is created, the return payload, the reversible/hidden-until-published lifecycle, and the auth requirement. It does not detail validation/error cases or how teacher/location are resolved, but nothing essential for a correct call is missing.

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 schema already documents all 8 parameters, including repeat_every_days and as_draft. The description reinforces the series behavior of repeat_every_days and the hiding behavior of as_draft but adds no syntax or format detail beyond the schema. Baseline 3 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?

States a specific verb and resource (creates one class or a recurring series from a class template) and clearly distinguishes the one-off vs series behavior via repeat_every_days. The UI analogy (Classes > Schedule > New Class) anchors the intent so an agent can identify it 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?

Usage is largely implied: the description explains as_draft keeps classes hidden and that cancel_class undoes the work, which implies when it is safe to run. But it never states explicit when-to-use/when-not conditions or names alternatives beyond the undo tool, so the agent must infer the right context.

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