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

Annotations already declare destructiveHint=true, so the mutation semantics are covered structurally. The description adds a useful constraint (only unfinished jobs can be cancelled) and the underlying REST endpoint, but says nothing about whether a running job is aborted mid-flight, whether cancellation is reversible, or what the response contains.

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, front-loaded with the action and constraint, with the endpoint given as a compact trailing reference. Nothing wasted.

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 single-parameter destructive tool with no output schema, the description covers purpose and the key state constraint. It could say more about post-cancellation job state, but nothing essential is missing for correct invocation.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents batch_id fully. The description adds no syntax or format detail beyond what the schema provides, which is the expected baseline for this ratio.

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 (batch job) with a state qualifier ('that has not finished'), so an agent can distinguish it from together_cancel_fine_tune and other siblings. It's clear, though it doesn't explicitly name the sibling it is not.

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?

'that has not finished' implies the precondition for use, but there is no explicit when-to-use routing, no mention of alternatives (e.g., get_batch to check status first), and no guidance on what happens if the job is already terminal.

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