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

With no annotations provided, the description carries the burden of behavioral disclosure. It clearly states the operation is non-destructive until a confirm step, which is valuable. However, it doesn't disclose what the prepare step actually returns (e.g., a mutation receipt or reference needed for confirm), nor any side effects or prerequisites.

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 no filler. The key behavioral fact ('Does not remove until confirm') is front-loaded and earns its place.

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 two-parameter prepare tool with no output schema, the description is adequate but leaves gaps: it doesn't explain what the agent should do with the result of prepare, what upload_ref refers to, or how this relates to the confirm sibling. The prepare/confirm pattern is inferable from the name and sibling list, but not fully specified.

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 50%: customer_id has a description ('10-digit Google Ads customer id.'), but upload_ref has none. The description adds no parameter-level meaning beyond the schema, so it doesn't compensate for the undocumented upload_ref. Baseline 3 is appropriate since half the parameters are documented in the schema.

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 ('prepare permanent removal') and resource ('one direct video upload'), and clarifies that it does not remove until confirm. This distinguishes it from the sibling google_ads_video_upload_remove_confirm, though it doesn't explicitly name that 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 description implies a two-phase prepare/confirm workflow by saying 'Does not remove until confirm,' which tells the agent this is the preparation step. However, it doesn't explicitly state when to use this tool versus the confirm variant or other removal tools, leaving the routing partially to inference.

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