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

Annotations only declare the generic non-read-only, non-destructive, non-idempotent profile. The description adds genuinely useful behavior beyond that: the source file is left unchanged, the call is asynchronous, and the output arrives via get_tool_execution rather than in the response.

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?

Three short sentences, each carrying distinct information: the action, the non-destructive guarantee, and the async result path. Front-loaded with the effect and no 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?

For a one-parameter async tool that has an output schema, the description covers everything an agent needs: what is produced, that the input is preserved, and how to retrieve the result. Nothing material is left implicit.

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?

There is a single parameter with 100% schema description coverage, and the schema already explains where to source the videoFileId. The description adds no parameter-level detail, so the baseline 3 applies.

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?

States a concrete verb and resource ('Create a new video with the background removed') plus the key scope fact that the source is untouched. An agent can distinguish it from remove_image_background purely from the 'video' resource in the first sentence.

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 explains the async handoff ('get_tool_execution provides status and results'), which tells the agent how to complete the operation, but it never states when to choose this tool over siblings like remove_image_background or the various generate_* tools. Usage is implied rather than directed.

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