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

Goes well beyond the annotations by describing cooperative cancellation semantics, partial completion at checkpoints, rejection conditions, compute accounting, and that the response is not proof of cancellation. This gives the agent rich behavioral context that annotations alone (destructiveHint, idempotentHint, etc.) do not convey.

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-loads the core purpose, then adds constraints, billing, return semantics, and alternatives in tightly packed but non-redundant sentences. Every sentence contributes distinct information.

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?

Despite having an output schema, it still usefully clarifies that the response is not proof of cancellation and directs the agent to poll job_get or job_wait. Combined with annotations and schema, nothing needed to invoke the tool correctly 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%, so the schema already documents both jobId and reason fully. The description adds no parameter-specific meaning, which is the baseline case when the schema does the heavy lifting.

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 ('cancel' a 'job') and immediately scopes it as cooperative cancellation for open jobs. It clearly distinguishes itself from job_get, job_wait, jobs_list, and job_report by naming their distinct roles.

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?

Explicitly says when to use it ('when an open job should stop'), when it will be rejected (terminal jobs or once result publication starts), and which alternatives to use for locating jobs, polling terminal state, or getting detailed results.

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