create_performance_max_campaign

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

With no annotations provided, the description takes on the full transparency burden. It discloses crucial behaviors: the campaign is created PAUSED, the two-phase validation prevents accidental creation, the entire operation is atomic ('If anything fails, nothing is created'), and it never uploads images ('this tool never uploads images'). It also mentions the allowlist requirement for customer_id, adding operational context.

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 description is structured effectively: it leads with the core purpose, then explains the two-phase flow, atomicity, and asset reuse, followed by a comprehensive but concise Args list. Every sentence adds necessary information, and the length is proportionate to the tool's complexity (20 parameters). It avoids redundancy and is front-loaded with the most critical facts.

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 complex mutation tool with 20 parameters and two-phase behavior, the description covers all essential aspects: purpose, usage phases, atomic behavior, asset reuse, parameter semantics, and related tool guidance. An output schema exists to describe return values, and the description does not need to repeat that. The description is sufficient for an agent to invoke this tool correctly without additional context.

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%, but the description compensates by explicitly defining all 20 parameters in the Args block. It gives constraints (e.g., 'at least 3' headlines, 'max 25 characters' for business_name), examples (language_ids: '1002 = French, 1000 = English'), and clarifies optional fields (target_cpa, target_roas). This turns a bare parameter list into actionable guidance.

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 action: 'Create a Performance Max campaign, PAUSED.' It also introduces the two-phase preview/confirm flow, which distinguishes it from simpler create tools. The resource (Performance Max campaign) and key attributes (paused, atomic, asset reuse) are clearly stated, setting it apart from siblings like create_shopping_campaign.

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 explains when to use the preview vs. confirm path ('Without a token... validates... Call again with the token to create it for real'). It also directs users to gaql_query for finding existing asset IDs, acknowledging an alternative tool. While it doesn't explicitly contrast with all campaign-creation siblings, the context is clear enough for an agent to select this tool appropriately.

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