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

The description discloses important behavioral traits beyond the annotations: it re-enables only still-paused campaigns, leaves campaigns the user changed alone, and explicitly states that it resumes real ad spend. The destructiveHint:true annotation is enhanced by explaining exactly what is affected and the financial consequence. No contradiction with annotations.

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 sentences, each packing critical information: what the tool does, mode-specific behavior, and a warning about real ad spend. No filler, no repetition of schema data. Front-loaded with the essential action and scope.

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?

Given the tool's complexity (two modes, scope options, campaign-specific release) and the absence of an output schema, the description covers the core behavior, edge cases (campaigns changed by user), and the consequence (real ad spend). It fully equips an agent to decide when and how to invoke the tool.

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 baseline is 3. The description adds value by explaining the semantics of the modes in a broader context (re-arming vs. overruling the budget), which enhances but does not fully duplicate the schema's enum descriptions. It also implies how scope, event_id, and campaign_id relate without restating them. A 4 is warranted for adding cross-parameter context.

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 begins with a specific verb ('release') and distinct resource ('Emergency Brake'), and clearly states the action's effect: re-enabling exactly the campaigns the brake paused. It differentiates from sibling tools by naming the two modes ('raise' vs 'resume') and by contrasting with brake-related tools like get_brake_status and set_budget.

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 description explicitly explains when to use each mode: 'mode='raise' re-arms the brake against the budget's current amount for the rest of the month; mode='resume' means the user knowingly overrules the budget, so that level stays disarmed until next month.' It also warns to confirm intent first, which is a clear usage condition. This exceeds the baseline by providing mode-specific decision guidance.

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