Cancel Batch

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds one genuinely non-obvious state-machine rule (a completed batch is a no-op), but omits the more important behavior for a cancel tool: what happens to an in-progress batch, whether partial results are discarded, and whether it requires authorization.

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 followed by the one caveat that matters. No filler, no restatement of the tool name.

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 simple one-parameter mutation with no output schema this is only adequate. The no-op edge case is covered, but the effect on a running batch, the return value, and batch_id provenance are all absent, leaving meaningful gaps for a destructive operation.

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%, so the schema documents nothing about batch_id, and the description provides no compensating detail about its format, where to obtain it, or whether it accepts an id from submit_batch. With one undocumented parameter, the description leaves the agent to guess.

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 ('Mark a batch cancelled'), which is enough to know what the tool does. It does not, however, differentiate itself from the adjacent cancel_run sibling, which an agent could easily confuse it with.

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?

'A finished batch stays completed' implies the useful precondition that cancelling is only meaningful for a non-finished batch. But there is no explicit when-to-use guidance, no mention of the cancel_run alternative, and no statement of prerequisites for obtaining a batch_id.

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