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

Annotations only tell the agent this is non-read-only, non-destructive and open-world; the description adds material facts they do not carry, notably that the ad is created PAUSED and that even a validate-only call has a real side effect (images land in the ad account's library). It stops short of describing what the call returns or how long Meta's review check takes.

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?

Roughly three sentences, all front-loaded: what is built, the PAUSED default, then the confirm workflow. Every clause carries operational information and nothing is redundant with the title.

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 non-idempotent, open-world write with a nested object and no output schema, the description covers the creative options, the PAUSED state and the confirm gate well. It is silent on the return value (ad id? validation errors?) and on whether a failed validation still leaves uploaded images behind, which matters for retry decisions.

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 50% and the nested ad object already documents most creative fields, so the schema does much of the work. The description adds useful disambiguation for the media fields (one image, a 2-10 image carousel, or a video) and explains the confirm flag's two-phase meaning, but says nothing about adset_id or page_id beyond what the schema implies.

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 concrete verb and resource ('Add an ad to an existing Meta ad set') and enumerates the creative pieces involved, so an agent knows exactly what gets built. It implicitly separates itself from Google's ads_create_ad by naming Meta and from meta_create_ad_set by requiring an existing ad set, but it never names meta_update_ad as the alternative for changing an ad after creation.

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 prescribes an explicit two-step protocol: call first without confirm to upload assets and validate, then call again with confirm: true to actually create. That is exactly the when-to-use and sequencing guidance an agent needs for a mutating tool, with no inference required.

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