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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is known. The description adds real value on top: the ENABLED gating prerequisites (owner approval, confirmed spend limit, verified offer evidence, bound booking target), the immediate effect of PAUSED, and that guardrailCheck runs spend-guard and landing-page checks. It still does not say what happens to running campaigns when ENABLED is applied or whether the prerequisite check fails loudly.

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?

Four short sentences, front-loaded with the action and then the mode-specific rules. Dense but each sentence carries information; no filler or repetition.

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?

This is a destructive, open-world mutation with 8 undocumented parameters and no output schema, so the description should do more: explain the required offerKey/planHash, what the two channels mean, and what the call returns or fails on. The prerequisite rules are helpful but leave half the contract unstated.

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 0% across 8 parameters, so the description must carry the meaning. It only implicitly covers status, ownerApproved, spendLimitConfirmed and guardrailCheck; the required offerKey, plus planHash, surfaceKey and channel, are never explained, and their formats/relationships (e.g. that planHash identifies the draft) remain opaque.

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 and resource: 'Wendet einen gespeicherten Steuerungsentwurf an' (applies a saved control draft). That is concrete enough to distinguish it from prepare_/get_ siblings by implication, but no sibling is named and the draft/apply relationship is only 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?

It gives conditional guidance for the two status values (ENABLED requires prerequisites, PAUSED pauses immediately), which implies when each mode is appropriate. It never says when to call this versus prepare_search_ads_campaign_control or get_search_ads_campaign_control, and never states that a prepared draft must exist first.

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