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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false. The description adds meaningful context beyond them: that credits are restored under normal rules and that a confirmation step is expected. It does not say what happens to partially completed work or whether cancellation is reversible.

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?

Two short sentences, zero padding, with the destructive action and the confirmation requirement front-loaded.

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?

An output schema exists so return values need not be described, and annotations cover the safety profile. However, with all three required parameters undocumented in both schema and description, an agent lacks guidance on the idempotency key and batch identifier for a destructive mutation.

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 0% and there are three required parameters. The description only gestures at 'confirmed' via 'Confirm first'; batch_id and the required idempotency_key (with its format/length constraints) are left entirely unexplained, so it does not compensate for the coverage gap.

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 (Cancel) and resource (unfinished batch work), which distinguishes it from read-only siblings like get_batch and from generation tools like accept_generation. It does not define what constitutes 'batch work' or how it relates to jobs, so it stops short of full differentiation.

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?

'Cancel unfinished batch work' implies the applicable state, and 'Confirm first' gives a procedural instruction, but no alternatives or exclusions are named (e.g., what to do for finished batches, or whether get_batch should be checked first).

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