Plan a Meta ad set

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description reinforces this with 'nothing is written'. Beyond the annotations it adds real behavioral context — the ad set is created 'always PAUSED', the parent campaign is 'checked', and critically 'No automatic rollback' — which an agent needs to know for recovery. It stops short of describing what the plan produces or any rate/limit behavior.

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 and front-loaded, leading with the PLAN/no-write qualifier before workflow and constraints. The parenthetical, telegraphic style is efficient but slightly choppy, which keeps it just short of ideal structure.

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 13-parameter, no-output-schema tool it covers the plan-vs-apply workflow, default paused state, ownership validation, and rollback behavior. It does not explain what the plan returns or how its result feeds meta_apply, which is the main remaining gap given the absence of an output schema.

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 100%, so the schema already documents all 13 parameters including enums and defaults, making 3 the baseline. The description adds only marginal parameter meaning — the bid-field policy constraint and the mention of validate_only (which is not even a declared parameter) — without clarifying individual fields beyond the schema.

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 states a specific verb and resource — 'PLAN ... create a Meta ad set' — and immediately qualifies scope with 'always PAUSED, in a campaign of the client's account (checked)'. The 'PLAN (nothing is written)' framing cleanly distinguishes it from sibling create/apply tools like meta_plan_create_ad and meta_apply.

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?

It explicitly names the alternative and the workflow: 'Dry-run with validate_only; apply with meta_apply', telling the agent exactly when to use this tool versus the apply sibling. It also states a when-not constraint ('No bid fields (bid caps are refused by the policy)'), removing guesswork about refused inputs.

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