wafle_ads_recommendation_apply

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

The description goes beyond the idempotentHint and destructiveHint annotations by explaining the idempotent behavior (re-applying returns previous result) and the queued behavior for human-judgment actions. This adds meaningful context about what happens when the tool is invoked, including the return value for queued actions.

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 concise and well-structured. It front-loads the core action, then covers idempotency and the special queuing behavior in a second paragraph, without unnecessary words or repetition.

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?

Although the description covers the main behavior and the queuing special case, it lacks detail on the general return structure (only mentions ok=true for queued) and error conditions. Given there is no output schema, the description carries more responsibility and could be more complete, but it still provides essential behavioral context.

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 provides a description for 'slug' but not for 'recommendation_id'. The description clarifies that the id refers to the recommendation being applied, which adds some meaning, but it does not explain the slug parameter beyond what the schema already states. With 50% schema coverage, the description offers only partial compensation.

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 clearly states the tool applies a wafle ads recommendation by id, runs the underlying writer action, and marks it as applied. It distinguishes this from direct actions like campaign pause by framing it as applying a recommendation, and the sibling list reinforces that distinction.

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 provides clear context for when to use the tool: when you have a recommendation id and want to execute it. It also explains special handling for human-judgment actions, but it does not explicitly contrast with alternative tools like wafle_ads_campaign_pause or wafle_ads_campaign_update_budget, though the context makes the use case obvious.

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