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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It explains the daily evaluation cadence, the AND-combination of conditions, the mandatory min_spend guardrail, the automatic ignoring of recent days for conversion-based metrics, and Meta's learning-phase protection. These are non-obvious behaviors that an agent must know to avoid misfiring on live spending.

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 dense but each sentence earns its place. It front-loads the purpose and the critical safety protocol, then provides guardrail and platform constraints. No fluff or repetition. It is longer than typical, but the complexity of the tool justifies the length. The structure flows logically from what→when→how.

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 tool with 11 parameters, nested conditions, and no output schema, the description covers the essential behavioral and safety context. It explains the daily check, modes, guardrails, AND logic, recency handling, and platform differences. It does not describe the return format, but since there is no output schema, that omission is acceptable. An agent could call this tool correctly with the information provided.

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 55%, so the description must compensate. It adds meaning for several critical parameters: mode (notify vs auto_act), min_spend (required, cannot be zeroed), conditions (AND semantics, conversion-metric recency exclusion), level (Google restriction), and dry_run (must preview first). It also clarifies account_id formats. However, some parameters like cooldown_hours and entity_ids are only minimally addressed, leaving gaps that the schema partially covers.

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 clear verb+resource: 'Create, change, switch on/off or delete an automation rule for one ad account.' It precisely enumerates the supported actions (create, update, enable, disable, delete) and specifies the scope (one ad account). This distinguishes it from sibling tools like adsap_list_automation_rules, which only lists rules, and other adsap_manage_* tools that target different entities.

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?

Provides explicit when-to-use guidance with a mandatory safety protocol: 'ALWAYS call with dry_run true first, read the parsed rule back to the user in plain language including its guardrails, and only call again with dry_run false after they explicitly confirm.' It also gives platform-specific constraints (Google supports campaign and ad_set levels only) and explains the two modes (notify vs auto_act). No alternative tool is named, but the usage context is unambiguous.

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