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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is covered. The description adds nothing beyond that: it does not say what stopping does to partial results, whether the optimization can be resumed, whether in-flight work or billing is lost, or what state the process is left in.

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?

A single short sentence with the verb front-loaded and zero filler. Nothing is wasted, though there is very little content to begin with.

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?

With full annotations and full schema coverage, the definition is minimally adequate to invoke the tool. But for a destructive mutation it omits what the agent would want to know before calling it – the effect on the running optimization and whether the action is reversible.

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 processId, reason, and the superadmin-only customerId. The description adds no parameter meaning beyond the schema, which is the expected baseline 3 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?

The description states a specific verb (stop) and resource (a running optimization process), so the agent knows exactly what the tool does. However, it does not differentiate from close siblings such as delete_optimization or trigger_optimization, leaving the agent to infer the stop-vs-delete distinction.

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 word 'running' implies the tool applies to in-flight processes, but there is no explicit when-to-use guidance, no statement of prerequisites (e.g. you need the processId of an active run), and no mention of the alternative delete_optimization for terminating a process permanently.

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