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

With no annotations, the description carries the full burden and does well: it discloses that cancellation is asynchronous, that the job settles with close_reason 'cancelled', and that finished/deleted jobs are unaffected. It stops short of stating permission/auth requirements or whether the call is idempotent on repeated invocation, which keeps it out of the top band.

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, front-loaded with the action, then the async caveat, then the no-op boundary. Every sentence carries distinct information and none is redundant.

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 mutation tool with no output schema, the description covers everything an agent needs: what it does, the async result shape (close_reason), the verification path, and the no-op case. Nothing material 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 coverage is 100% and the single 'job' parameter is documented in the schema with its project/spider/job format and pattern. The description adds no parameter-level detail beyond what the schema already provides, so the baseline 3 applies.

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: 'Stop a pending or running Scrapy Cloud job.' The scope qualifier ('pending or running') and the explicit no-op condition ('Does nothing for finished or deleted jobs') separate it cleanly from siblings like scrapy_cloud_get_job and scrapy_cloud_delete_periodic_job.

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?

Gives both sides of the when-to-use boundary: applicable to pending/running jobs, ineffective for finished or deleted jobs. It also names the follow-up tool ('poll scrapy_cloud_get_job to confirm'), so an agent knows the workflow rather than just the call.

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