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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description usefully adds that child work started by the job is also stopped, but says nothing about graceful vs forced termination, retention of partial output, or the error behavior implied by non-idempotency.

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?

One sentence, zero waste, and the scope-expanding clause is placed where it is most informative.

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?

Acceptable for a mutation tool whose annotations carry the safety profile and which has no output schema. But the 50% parameter coverage gap and missing guidance on job_id acquisition and post-stop behavior leave real holes.

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 50% — the required job_id has no description, while server does. The description adds no meaning for job_id (no format, no source for obtaining it), so the undocumented half of the parameters is unaddressed.

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 (stop) and resource (running background job) and adds scope detail — 'and everything it started.' An agent can distinguish it from start_job/list_jobs, though no sibling is named explicitly and the correlation with job_output is left implicit.

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?

No when-to-use guidance, no prerequisites, no alternatives. Nothing tells the agent whether this is for active jobs only, what happens if the job already finished, or how it relates to list_jobs/wait_for_approval.

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