zuckerbot_recommend_campaign_structure

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

With no annotations, the description carries full burden. It discloses key behavioral traits: uses Claude for data-driven recs, defaults for cold start, returns comparable_historical_cpl with source and disclaimer, never CPL projection, and lead destination defaults. It also mentions the recommendation should be presented for approval. However, it does not explicitly state read-only nature or potential side effects (though it's a recommendation, so likely safe). Overall, good transparency for a non-destructive tool.

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 about four sentences, efficient and front-loaded with the main purpose. It includes essential details without fluff. A minor improvement could be more compact phrasing, but overall it's well-structured and easy to parse.

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 (8 params, nested objects, no output schema), the description explains the main behavior and output elements (comparable_historical_cpl, disclaimer) but lacks detail on the full output structure of the recommendation. It mentions components like 'audience tiers, budget allocation, creative mix' but does not specify how these are returned (e.g., separate fields or nested object). This leaves some gap for an AI agent to understand the response format.

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%, so baseline is 3. The description adds context for lead_destination (reiterating schema) and explains overall behavior but does not add significant new meaning to individual parameters beyond what the schema provides. The description's main value is in tool-level context, not parameter-level semantics.

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 'Generate a campaign structure recommendation' and specifies components (audience tiers, budget allocation, creative mix). It distinguishes between accounts with history and new accounts, and uses specific verbs like 'generates' and 'returns'. The purpose is unambiguous and differentiates from sibling tools like zuckerbot_create_campaign which actually creates campaigns.

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 provides clear context on when to use: generating recommendations before proceeding to creation. It explains behavior for accounts with history vs cold start, and gives guidance on lead_destination for lead campaigns. However, it does not explicitly mention when NOT to use this tool or name alternative tools (e.g., use zuckerbot_create_campaign instead for direct creation). The guidance is good but lacks explicit exclusions.

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