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

With no annotations, the description correctly discloses a key behavioral trait: it does not mutate Google Ads. However, it does not explain what preparation actually does, what it returns, or what constraints apply beyond the parameter names.

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?

Two short sentences with the action and object front-loaded and a useful safety qualifier in the second sentence. There is no filler or redundancy.

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 tool with four required parameters, no output schema, and no annotations, the description is too sparse. It omits the expected return/receipt, how the prepared upload should be used with the confirm step, and important format constraints. An agent cannot confidently complete the prepare-to-confirm flow from this description alone.

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 documentation covers only customer_id, and the description adds only that base64_data is image data. It does not explain accepted content_type values, filename expectations, or base64 encoding requirements. With 25% schema coverage, the description undercompensates for the undocumented parameters.

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 names a specific action ('prepare'), a specific resource ('image asset upload'), and the input format ('base64 image data'). The qualifier 'No Google mutate' clearly differentiates it from the asset_upload_confirm sibling.

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 'prepare' verb and 'No Google mutate' imply this is a pre-mutation step before an upload confirm, but the description does not explicitly name the confirm sibling or say when to choose this over video_upload_prepare. Usage context is present but mostly relies on naming conventions.

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