Update Ad Set

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

Annotations are all false, so the description carries the burden. It adds useful behavioral context: 'Only provided fields are changed' and the caveat about soft opt-out allowing up to 5% spend. However, it does not disclose permissions, reversibility, side effects, or what happens when fields are omitted beyond the stated partial update.

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 compact, front-loaded with the core purpose, and uses a clear bulleted list for arguments. Every sentence adds value, and the 'Only provided fields are changed' note is placed prominently. No redundant fluff is present.

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 tool with 7 parameters and no output schema, the description covers all key behavior and parameters except response_format. It explains scoping (only provided fields change), the soft opt-out caveat, and field formats. Missing return-value details and prerequisites are minor given the tool's straightforward update action.

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 only 29%, and the description compensates well by explaining most parameters in plain terms: daily_budget in cents, end_time in ISO 8601, status enum values, and placement_soft_opt_out behavior. However, it omits the response_format parameter entirely, which is present in the schema and has its own description, so not all parameters are covered in the description.

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 operation with a verb and resource: 'Updates an existing ad set. Only provided fields are changed.' It also communicates partial-update semantics, which distinguishes it from a full replace. It doesn't explicitly name sibling tools like meta_update_ad or meta_update_campaign, but the resource is 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?

The description implies usage through the verb 'updates' and the resource 'ad set', and the phrase 'Only provided fields are changed' implies a PATCH-like behavior. However, it gives no explicit 'when to use this vs. meta_create_adset or meta_update_ad' guidance, and no conditions or exclusions are stated.

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