meta_ads_excluded_placements_set

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

With no annotations provided, the description carries the full burden and exceeds it: it discloses mutation ('Mutating and delivery-affecting'), the specific risk of zero delivery, the replace-not-append semantics, the merge behavior preserving other targeting, return values ('Returns ad_set_id, the applied facets, and Meta's update result'), and side effects ('Recorded in STATE.json's action_log' and 'reversible via rollback_apply'). This is exemplary disclosure for a mutation tool.

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 front-loaded with the core purpose and return value, then layers risk, replacement semantics, merge behavior, and state/rollback side effects. Every sentence adds distinct, non-redundant information, and the whole thing is appropriately sized for a complex mutating tool — no 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?

Given there is no output schema and no annotations, the description covers all essential context: what it does, what it returns, the mutation risk, the replace semantics, what is preserved, and the rollback/logging path. The only minor omission is permission requirements, but the description is otherwise complete for an agent to select and invoke this tool safely.

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 100%, and each parameter already has a detailed description, so baseline is 3. The description adds genuine value beyond the schema by generalizing the replacement rule ('Each supplied facet REPLACES its current value... an omitted facet is left untouched'), which clarifies omission behavior not stated per-field in the schema. It also frames the read-modify-write merge across facets.

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 opens with a specific verb+resource: 'Sets one ad set's delivery-surface exclusions.' This clearly distinguishes it from the sibling meta_ads_excluded_placements_get (getter vs setter) and from Google Ads negative placement tools. The scope ('one ad set') and platform (Meta) are explicit.

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?

The description implies the read-before-write workflow via 'read-modify-write merge' and warns of the risk ('excluding too much can take an ad set to zero delivery'), giving clear caution about when to use it. However, it does not explicitly name the alternative meta_ads_excluded_placements_get or state when not to use this tool — that guidance lives in the schema rather than the description.

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