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

Discloses key behaviors: terminal state, irreversibility, release of remaining budget, and output format. These go beyond the annotations (e.g., idempotentHint, destructiveHint) and provide critical context for invocation. 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?

Structured into clear sections (tool_description, when_to_use, combination_hints, output_format) with minimal fluff. Slight redundancy in repeatedly stating terminal/irreversible, but overall efficient and front-loaded with purpose.

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?

Complete for the tool's complexity. Covers purpose, usage timing, behavior, and output. With siblings like pause and activate, the distinction is clear. No return schema exists, but the output_format section adequately describes the response.

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% for both parameters, each with clear descriptions (reason, media_buy_id). The tool description does not add parameter-specific semantics beyond the schema, but baseline 3 is appropriate as the schema carries the burden.

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 clearly states the action: 'Cancel a media buy campaign.' It also specifies the terminal nature, distinguishing it from temporary operations like pause. The verb+resource is specific and unambiguous.

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?

Provides explicit when_to_use guidance: 'When an advertiser wants to permanently stop a campaign. Cannot be undone. Use pause for temporary stops.' This directly addresses alternatives and exclusions, making it easy for an agent to decide between cancel and pause.

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