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

Annotations already indicate a non-read-only, non-destructive operation. The description adds valuable behavioral context beyond annotations: the action is created locally and only gains a remote id and tag snippet through sync, and it is scoped to the active Space with an override option via space_id. This informs the agent about side effects and state, going beyond the basic mutation flags.

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 three sentences, front-loaded with the primary purpose, and every sentence earns its place by explaining key concepts (local creation, sync, space scoping). There is no redundancy or fluff, making it highly concise and well-structured.

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?

Given the nested body object and no output schema, the description adequately explains the tool's role, local creation vs export, and space override behavior. It does not describe the return value, but this is not required since no output schema is present. The context provided is sufficient for correct tool invocation, though it could mention what happens on success (e.g., returns the newly created action) to be fully complete.

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 100%, so the schema already documents all parameters with descriptions. The description only repeats the requirement for body's minimum fields ('at least { name, type, category }') which is also present in the body description, and adds no unique parameter-level detail. Baseline 3 is appropriate because the schema handles the heavy lifting.

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 states a specific verb ('Create') and resource ('a conversion action'), defines it as 'the thing an uploaded conversion is counted against', and distinguishes it from sibling tools like create_conversion_source and upload_offline_conversion by explaining that creation is local and exporting happens through campaign sync. This makes the tool's purpose unambiguous and clearly differentiated.

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 gives clear workflow context: 'created locally' and 'exporting ... happens through campaign sync', indicating when to use this tool within a larger process. It also explains space scoping and points to set_active_space as an alternative for switching spaces. However, it does not explicitly state when not to use this tool versus other create_* tools, though the distinction is implied.

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