Plan a Meta ad

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

Annotations already declare readOnly=true and destructive=false, so the safety bar is lower. The description adds real value beyond them: the ad is 'always PAUSED', the creative must be existing and the ad set/client are 'both checked', and there is 'No automatic rollback'. That last point is important operational context an agent cannot get from the schema.

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?

One tightly packed sentence group with the critical constraint ('nothing is written') front-loaded first. Every clause – paused state, creative source, dry-run/apply routing, no rollback – earns its place with zero filler.

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?

No output schema exists, but the description covers the mutation semantics, the validate_only safety gate, the apply follow-up, and the rollback limitation. For a 4-param planner this is nearly complete; only the plan's return/handle (e.g. how to reference it in meta_apply) is left implicit.

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 documents all four parameters (name, adset_id, client_id, creative_id) with formats and defaults. The description restates the parent ad-set/creative relationships but adds no syntax or format detail beyond the schema. Baseline 3 is correct.

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 ('create a Meta ad') and immediately scopes it with 'PLAN (nothing is written)', which distinguishes it from the sibling meta_plan_create_campaign and meta_plan_create_adset. An agent can tell exactly what this does and that it produces a plan rather than a live entity.

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?

Clearly routes the agent through the workflow: 'Dry-run with validate_only; apply with meta_apply.' This names the alternative (apply) and the condition that selects it. It doesn't explicitly contrast against sibling planners, but the plan/apply pattern is unambiguous.

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