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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful billing/skip semantics for pending vs in-flight cells, but this is largely redundant with the destructiveHint=false annotation and doesn't describe auth or reversibility beyond that.

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?

Front-loaded with the core action and its key behavior in the first clause. The inline example is helpful but slightly repetitive given the schema example already provides the same shape.

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 cancellation tool with no output schema, the description covers the critical billing and skip semantics an agent needs. It's complete enough, though it could note any permission or confirmation requirements.

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 parameter is documented as coming from experiment_create. The description's example adds a concrete value but no new semantic detail beyond the schema.

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 (running experiment), and precisely defines the semantics: pending cells are skipped, in-flight cells finish and bill. This distinguishes it from siblings like experiment_status or experiment_list.

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 description makes clear this applies to a running experiment and explains the partial-cancellation behavior, giving strong context for when to use it. It does not, however, name alternatives or state when not to use it.

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