direct_ads_set_state

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

With no annotations, the description carries the burden of disclosing mutation. It does label the tool as 'WRITE' and instructs 'allow_write=true', which is useful. However, it omits other behavioral details like dry-run behavior or reversibility, leaving some gaps.

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 extremely concise, with four terse fragments that pack essential information. It is front-loaded with the purpose and includes the critical allow_write requirement without any 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?

The tool has 5 parameters and no output schema, yet the description is minimal. It covers the core action and the allow_write requirement, but leaves dry_run behavior unexplained and does not describe return values or side effects, making it adequate but incomplete.

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?

The description adds meaning for ad_ids by clarifying that int64 values can be passed as number or string, which is absent from the schema. It does not explain dry_run or elaborate on the 'project' parameter beyond a vague 'via parent campaigns', and schema coverage is only 40%.

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 explicitly starts with 'WRITE:' and lists the actions 'suspend | resume | moderate' on 'ads', clearly defining the tool's verb and resource. This differentiates it from sibling tools like direct_suspend_campaigns or direct_set_keyword_states.

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 clearly identifies the resource ('ads') and the actions, giving an agent strong context for when to use it. However, it does not explicitly mention alternatives or exclusions, so it falls short of a full 'when-not' guidance.

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