ads_update_adset

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It correctly notes that changing budget, bid, targeting, or optimization restarts learning, and that day-parting requires lifetime budget and pacing_type. This is valuable context, but it omits other important behaviors such as permission requirements, the meaning of the 'confirm' parameter, or whether changes are reversible.

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: a main sentence plus two concise caveat notes. It is front-loaded and each sentence provides actionable information without redundancy. It could be slightly more structured, but it is appropriately sized for the content.

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 19 parameters, no output schema, and no annotations, this description is incomplete. It covers the core function and critical caveats, but does not explain optional-field semantics, the purpose of `confirm`, expected return behavior, or operational prerequisites. The high parameter count and zero schema coverage demand much more contextual detail.

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?

The schema has 0% description coverage, so the description must compensate. It explains special requirements for `adset_schedule` and identifies fields that trigger learning restart. However, with 19 parameters, the vast majority (name, status, start_time, bid_strategy, etc.) are left semantically unexplained, leaving significant gaps for an agent.

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 uses a specific verb+resource: 'Update fields on an existing ad set.' This clearly distinguishes the tool from siblings like ads_create_adset, ads_get_adset, ads_delete_adset, and ads_pause_adset. It also mentions an alternative tool for day-parting, reinforcing the specific scope.

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 gives clear context for use: it targets existing ad sets and highlights when special constraints apply (learning restart, day-parting requirements). It explicitly names ads_set_adset_schedule as an ergonomic alternative for day-parting. However, it does not broadly discuss when to avoid this tool in favor of other update tools beyond the schedule case.

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