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

Annotations already flag it as a non-read-only, non-destructive, non-idempotent open-world write, so the bar is lower; the description still adds real context by disclosing that the ad set is created PAUSED and that the first call creates nothing. What's missing is anything about failure modes, permission requirements, or what happens when the campaign is in an incompatible state.

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?

Four short front-loaded sentences: what it creates, key fields, resulting state, then the two-step confirm protocol and next step. Nothing is redundant and the safety-critical confirm sequence is easy to find.

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?

With 12 parameters, low schema description coverage, and no output schema, the description should say more about the unlabeled scheduling and tracking parameters (page_id, pixel_id, start_time, end_time) and about what the confirmation result returns. The confirm protocol and PAUSED state are well covered, but the definition is not complete for a tool of this complexity.

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 only 17% across 12 parameters, so the description carries weight and does explain goal, daily budget, locations, ages, and the validate-then-confirm flow for confirm. However, page_id, pixel_id, start_time, end_time, and campaign_id are not explained anywhere, so it only partially compensates for the low coverage.

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?

States a specific verb and resource ('Add an ad set to an existing Meta campaign') plus the key configuring fields (goal, daily budget, locations, ages). It also distinguishes itself from siblings by naming meta_create_ad as the follow-up step, so an agent can tell it apart from meta_create_campaign and meta_create_ad.

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?

Gives explicit sequencing guidance: call without confirm first so Meta validates, then re-call with confirm: true. It also tells the agent what to do next (add ads with meta_create_ad). It doesn't cover alternatives like meta_build_campaign or prerequisites such as needing a connected Meta account, but the core when/how is clear.

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