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

Adds substantive behavior beyond the annotations: the ad keeps its history, gets a new creative, and goes into Meta review — context that explains why destructiveHint is set even though the edit is versioned. The validate-only preview behavior is also spelled out. It does not cover permission/special-ad-category constraints or what the validation response returns.

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?

Three tight sentences: what it changes, what happens server-side, then the required call order. The preview instruction is placed last where it will be read before invocation, and no sentence is 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?

For an eight-parameter mutation with no output schema, the definition covers scope, side effects, and the confirm/preview workflow adequately. Remaining gaps (whether omitted fields are preserved, review latency, failure modes) are modest but would matter to an agent editing a live ad.

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 only 13%, so the description must carry the load, and it does: it maps six of the eight parameters to concrete concepts (primary_text, headline, description, link_url, call_to_action, phone_number). It leaves ad_id obvious-by-name and does not enumerate the allowed call_to_action values, though the enum is self-documenting in 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?

States a specific verb plus the exact editable fields (primary text, headline, description, link, button, phone number), so an agent knows precisely what this mutates. It implicitly separates itself from meta_create_ad and meta_set_ad_status by scope, though it never names those siblings explicitly.

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 an explicit call sequence: 'Call without confirm first' so Meta validates the change, which is a real when-to-use rule most tools lack. It stops short of naming alternatives (e.g., use meta_set_ad_status for pausing), so routing against siblings is still partly inferred.

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