direct_add_audience_targets

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

With no annotations, the description is responsible for disclosing side effects. It does state 'WRITE' and mentions 'allow_write=true', which signals a mutating operation requiring explicit consent. However, it omits crucial behavioral details such as potential duplicate creation, validation of retargeting list IDs, idempotency, or any error conditions.

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 exceptionally brief and front-loaded with the WRITE label, but it uses telegraphic syntax that sacrifices clarity. It conveys the core purpose in a compact form but omits necessary elaboration, making it more under-specified than properly concise.

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 no annotations, no output schema, and a sparse description, leaving many gaps. It does not disambiguate from sibling tools, explain return values, or mention prerequisites like the need for existing retargeting lists and valid ad groups. For a write operation, this level of context is insufficient.

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 schema already documents 'project' and 'allow_write', but the nested fields (adgroup_id, retargeting_list_id, context_bid_rub) have no descriptions. The description merely lists these field names, adding no semantic meaning such as what adgroup_id refers to or how context_bid_rub is used. The question mark on context_bid_rub only reflects optionality already encoded in the required array.

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 labels this as a WRITE operation for 'audiencetargets.add' and lists the expected fields, clearly indicating it adds audience targets. This distinguishes it from read-only or state-modifying siblings. However, it relies heavily on the tool name and API endpoint naming rather than a natural-language statement.

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?

No guidance is provided on when to use this tool versus alternatives like direct_list_audience_targets or direct_audience_targets_state. The mention of 'allow_write=true' is a safety flag, not usage context. The agent must infer from the tool name and field list.

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