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

Annotations already indicate destructive and non-read-only behavior; the description adds that only running jobs are affected and that a job must have returned `job_complete: false`. This is useful behavioral context beyond the structured annotations.

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?

The description is concise, front-loaded with the core action, and each sentence adds relevant context. No filler or redundant restatement of the schema.

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 cancellation tool with fully documented parameters, clear annotations, and a known trigger condition, the description is complete. It gives the agent enough to call the tool correctly without missing prerequisites or ambiguous behavior.

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%, so each parameter is documented. The description adds meaningful provenance for jobId, explaining that it comes from execute_sql or execute_sql_readonly, which helps an agent supply a correct value.

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?

The description states a specific verb ('Cancel'), a specific resource ('running BigQuery job'), and even clarifies the trigger condition (`job_complete: false`). This clearly distinguishes the tool from sibling tools like execute_sql or get_query_results.

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 clearly says when to use the tool: to cancel a currently executing query job returned by execute_sql or execute_sql_readonly. It does not explicitly state when not to use it, such as ignoring completed jobs, but the context makes the intended use unambiguous.

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