Cancel Python metric preview

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

Annotations already declare this destructive, non-idempotent and non-read-only, so the agent knows it is a state-changing cancel. The description adds nothing beyond that: it does not say whether partial results are discarded, whether the preview transitions to a terminal 'cancelled' state, whether already-completed previews error out, or whether the operation is recoverable.

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?

A single front-loaded sentence with zero wasted words. It is efficient but borders on under-specification rather than conciseness, since the brevity comes at the cost of behavioral detail.

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 destructive, non-idempotent mutation with no output schema, the description should say what the caller gets back and what state the preview ends in. Those gaps are not covered by the annotations, which only flag risk level, leaving the agent without the outcome information it needs.

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 coverage is 100% with only two parameters, both fully described (immutable draft ID, asynchronous preview ID), so the baseline is 3. The description contributes no additional parameter meaning, such as how the two IDs are obtained or what happens on mismatched pairs.

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?

Names a specific verb (cancel) and a specific resource (Python metric preview), and the 'in-progress' qualifier scopes which previews it applies to. Siblings like create_python_metric_preview and get_python_metric_preview are clearly different operations, though the description never names them explicitly.

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?

'In-progress' implies the precondition that the preview must still be running, which is real implied guidance. But there is no statement of when to cancel versus letting it finish, no mention of what happens if the preview already completed, and no reference to the create/get sibling tools for context.

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