Draft conversion action changes

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

Beyond annotations, the description clarifies that this tool only returns a preview and does not execute changes until confirm_and_apply is called. Also explains partial-update semantics, which is important for user expectations.

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 compact and front-loaded with the core purpose, then gives practical usage instructions. No redundant information or 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?

Covers the full workflow: how to identify the target entity, what parameters are sent, what the response contains (plan_id), and how to commit the change. Adequate for an agent to use this tool correctly among many related siblings.

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 description coverage is 0%, and the description only vaguely references call-duration threshold and attribution. Many domain-specific parameters (counting_type, attribution_model, always_use_default_value, include_in_conversions_metric, window days) are not explained, leaving ambiguity about allowable values and meanings.

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?

Clearly states it drafts a partial UPDATE of an existing ConversionAction and returns a PREVIEW, which distinguishes it from create/remove actions. Lists specific use cases like rename, demote, change value, adjust call-duration threshold, and change attribution.

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 scenarios and explains that only non-empty/non-default parameters are sent. Includes concrete next steps: find the ID via the SELECT query and call confirm_and_apply with the returned plan_id to execute.

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