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 description earns credit for going further: it discloses that deletion is a *soft* delete (data not hard-removed), that a token gates the call, and that stale tokens are rejected. It stops short of saying whether the soft-delete can be restored or what happens to the automation's run history.

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, zero filler, and the most decision-critical fact (destructive soft-delete) is front-loaded before the preconditions. Every clause carries operational weight.

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 destructive mutation with no output schema, the description covers the safety contract (preview → confirm → token) that an agent most needs. It is slightly incomplete on post-conditions — no statement of what the caller sees on success or what happens to dependent runs — and notably the schema marks zero parameters required despite the description saying the token is required.

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 71%, so the schema carries most parameter meaning, but the description adds real semantics for confirmation_token — that it must be current and that stale values are rejected — which the schema's bare type declaration does not convey. automation_id remains undescribed in both places.

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 the operation type precisely ("Destructive and idempotent soft-delete") and names the sibling tool it pairs with (preview_automation_deletion), which separates it from update_automation and pause_automation. The resource (an automation) is only implied via the tool name rather than stated in the description text, which keeps it just short of a 5.

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?

Explicit gating: only call after preview_automation_deletion was shown AND the user explicitly confirmed in a new turn. It also names the precondition artifact (current confirmation_token) and the failure mode (stale tokens rejected), leaving nothing about when-to-call to inference.

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