Pre-flight check campaign rows BEFORE creating. Read-only. Per-row verdict: will_create / will_create_with_changes / will_fail. Pass meta_account_id to also check spend guardrails.
| Name | Required | Description | Default |
|---|---|---|---|
| campaigns | Yes | ||
| meta_account_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true. Description adds value by explaining the per-row verdict types (will_create, will_create_with_changes, will_fail) and the optional guardrail check with meta_account_id. No contradictions.
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?
Description is extremely concise: a single sentence plus a fragment. Every word earns its place, with the purpose front-loaded. No redundancy or wasted text.
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 validation tool with no output schema, the description covers purpose, read-only nature, verdicts, and optional guardrail check. It lacks explicit details on the return format (e.g., list of objects), but the verdict types imply the structure. Annotations provide the destructive hint.
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?
Top-level schema parameters lack descriptions (0% coverage). The description adds meaning for meta_account_id ('to also check spend guardrails') but only refers to campaigns as 'campaign rows' without further detail. The schema's nested item descriptions compensate partially.
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?
Description uses specific verbs: 'Pre-flight check campaign rows BEFORE creating.' It clearly identifies the tool as a validation/dry run, distinguishing it from creation siblings like bulk_create_campaigns. The read-only nature and per-row verdicts are explicitly stated.
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?
Description advises using this tool 'BEFORE creating', which provides clear context. It also notes that passing meta_account_id adds guardrail checks. However, it lacks explicit exclusions or direct mentions of alternative tools for creation, though the sibling list makes this obvious.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes, but creation tools (create_campaign, bulk_create_campaigns, create_structured, add_ad_to_adset) overlap in scope, potentially causing misselection. However, descriptions clarify differences.
All tool names follow a consistent verb_noun pattern in snake_case, such as 'bulk_create_campaigns', 'get_insights', 'pause_campaigns'. No mixing of conventions.
23 tools cover the Meta Ads domain well, but the count is slightly high. Most tools are justified, though some could be merged (e.g., creation variants).
Core CRUD is covered for campaigns and ads, but there is no tool to create an ad set independently (only via create_structured). Creative editing and standalone ad set creation are missing, leaving notable gaps.