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

Although annotations already include idempotentHint and destructiveHint, the description adds meaningful behavioral context: 'Soft delete — it stops being scheduled immediately and the schedule regenerates automatically,' 'The asset is retained and stops being scheduled; it is not erased,' and 'Affects one video.' These details clarify what a destructive hint means in practice (not permanent erasure) and what the side effects are, going well beyond the structured annotations.

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, with the main action front-loaded. Each sentence adds value: the operation, the soft-delete behavior and side effects, and the scope contrast with archive_channel. There is no redundancy or unnecessary detail.

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 one parameter, no output schema, and annotations, the description covers the key aspects: what is affected (one video), the immediate effect (stops scheduling), the subsequent behavior (schedule regenerates), the idempotency and retention, and the alternative when a whole channel needs removal. This is complete for the tool's complexity.

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?

The input schema only defines asset_id as an integer with no description, and schema description coverage is 0%. The description does not explicitly explain asset_id, but the tool name and 'Remove a video from a channel' make it evident that asset_id identifies the video to be removed. This partial compensation is enough for a single obvious parameter, but not fully explicit.

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 opens with 'Remove a video from a channel,' which is a specific verb+resource construction that clearly states what the tool does. It also differentiates itself from the sibling tool archive_channel by noting that 'archive_channel takes a whole channel off the air' and that this tool 'Affects one video.' This makes the purpose unmistakable.

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 explicitly contrasts this tool with archive_channel, telling the agent when to use delete_asset (for a single video) versus an alternative (for a whole channel). It also provides context that this is a soft delete that immediately stops scheduling and regenerates the schedule, which guides selection for use cases where retention of the asset is desired.

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