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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds real value on top by stressing the operation is permanent and by steering the agent to a non-destructive alternative, which is exactly the context an agent needs before an irreversible call. It does not cover what happens if the automation is still running or whether dependent nodes are affected.

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?

Two short sentences, zero filler, with the destructive scope stated first and the safer alternative second. Every sentence earns its place and the ordering matches the agent's decision order.

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 permanent-delete tool with no output schema and annotations covering destructuring and idempotency, the definition is nearly sufficient: it states the effect, its permanence, and the preferred alternative. It could still mention recovery impossibility or required scope/permissions, and it leaves flowId provenance to inference.

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%: idempotencyKey is thoroughly documented in the schema, while flowId has no description at all. The description adds nothing about parameters, so it neither compensates for the undocumented flowId nor explains where to obtain one. Given the single undocumented parameter is largely self-explanatory from context, a baseline 3 is appropriate.

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 plus the permanence qualifier: 'Delete a flow permanently.' It also names the softer alternative (set_automation_active), which helps discriminate from sibling delete_* tools. Minor ambiguity: it calls the resource a 'flow' while the tool and siblings use 'automation', and delete_whatsapp_flow exists in the same sibling set, so a small amount of terminological clarification is missing.

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 tells the agent when NOT to use this tool and names the alternative that should be preferred: 'Turning it off with set_automation_active is usually enough.' That is a concrete routing rule, not implied usage, and it is the most decision-relevant sentence in the definition.

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