run_custom_tool

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

With no annotations provided, the description carries the full burden. It only states the action ('Execute') and the identifier, but omits behavior like whether execution is asynchronous, whether it returns a result or a job ID, what errors may occur, or whether a Google account connection is required. Sibling 'flow_status' suggests status polling, but this is not mentioned here.

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?

A single sentence with no wasted words; the examples are integrated without bloat.

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 moderate complexity with an object parameter and no output schema, yet the description doesn't explain execution flow, return values, or prerequisites. Given the sibling flow_status, the absence of async/status info is a clear gap.

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?

All 4 parameters have descriptions in the schema (100% coverage), so the baseline is 3. The description repeats tool_id's URL/ID format but adds no extra semantic detail about inputs, prompt, or project_id.

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 uses the specific verb 'Execute' and names the resource ('custom or shared Google Flow tool'), with concrete examples like Type Overlays, Video Resizer. This clearly distinguishes from siblings such as update_custom_tool and list_tools.

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 examples of tool kinds it can run, implying use for those cases, but it does not explicitly state when to prefer this over built-in generators like generate_image or when not to use it. No exclusions or alternatives are mentioned.

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