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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description earns credit for disclosing behavior beyond those hints: running jobs are not interrupted, only pending/queued rows are cancelled, and succeeded files remain downloadable – exactly the partial-cancellation semantics an agent needs to set expectations.

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 short sentences, zero filler, with the core action and its scope front-loaded before the two caveats. Every sentence contributes a distinct fact.

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 one-parameter destructive tool with no output schema, the description covers the essential post-conditions (running jobs, succeeded files) and the safety hints come from annotations. It stops short of stating the response shape or the resulting batch status, but nothing critical for correct invocation 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% and the single batch_id parameter is documented with its pattern, so the schema carries the burden. The description adds no format or sourcing detail about batch_id beyond what the schema provides, making the baseline 3 correct.

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 rows') and scopes it precisely to 'pending and queued' rows. It is clear on its own, but it never references the closely related sibling retry_batch, so the agent gets no explicit differentiation between cancelling and retrying a batch.

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?

The scoping to 'pending and queued' rows implies when cancellation is meaningful, and the note that running jobs finish implies a use case where partial cancellation is acceptable. However, there is no explicit when-to-use statement, no prerequisites (e.g. batch must not be complete), and no pointer to retry_batch as the alternative for failed rows.

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