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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes much further, disclosing that two actions create drafts that do not publish, that boost_winner creates a PAUSED boost so no spend occurs yet, and that the other actions write standing autopilot state. That is exactly the safety-relevant context an agent needs before invoking a multi-mode mutation.

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?

The leading clause establishes the core action and the action-by-action clauses follow in a logical order with no filler. It is dense and runs long as a single semicolon-chained block, which slightly hurts scanability, but every clause carries information.

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 branching mutation tool with no output schema, the description covers all branches and their side effects well. The one gap is that it does not indicate what the call returns (e.g., the created launch id or the autopilot config change), which an agent would need for follow-up calls like get_launch.

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 100% and the schema already states ad_account_id is required for boost_winner and ignored otherwise, so the description largely restates it. It adds only the implicit framing that ad_account_id is conditionally relevant by action type, which is a marginal gain over the structured field.

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 opens with a specific verb and resource ('apply a recommendation's one-click action') and then enumerates every action variant (repost_winner, cross_post, boost_winner, promote_winner, pause_underperformer) with its concrete effect. This makes it clearly distinguishable from dismiss_recommendation, which is the natural near-miss sibling.

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?

By mapping each action type to its consequence, the description tells the agent what will happen when it chooses to apply, and the parentheticals ('nothing publishes until scheduled', 'activation, and therefore spend, is a separate step') clarify follow-on steps. It stops short of explicit when-not-to-use guidance or of directing the agent to dismiss_recommendation instead, and it never says where recommendation_id comes from.

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