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

Annotations already declare this as destructive, non-readonly, and non-idempotent, so the baseline burden is lower. The description adds valuable behavior beyond annotations: the prior variant is retired only after the new variant saves successfully, and the result includes an editor link. It could say more about failure behavior or irreversibility, but the core transactional behavior is disclosed.

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 two front-loaded sentences with no wasted text. It states the main action first and then adds the important replacement condition.

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 output schema exists, so the description need not document return values in depth, and annotations cover the destructive nature of the operation. Still, for a destructive mutation with three required but poorly documented parameters, the description leaves important parameter semantics and prerequisites unclear.

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 only 25%, so the description must compensate for undocumented required parameters. It adds meaning for replaceVariantId, explaining that the prior variant is retired only after a successful save, but it does not clarify projectId, candidateId, or candidateKey, including the distinction between the candidate identifier and its hash-like key.

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 and resource: it saves a prepared promo-video candidate as a variant and returns an editor link. It is clear what the tool does, though it does not explicitly distinguish itself from siblings such as create_variant or preview_promo_video.

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 word 'prepared' implies a candidate must first exist, and the replaceVariantId sentence gives a conditional usage rule. However, the description does not say when to choose this tool over related tools like create_variant, preview_promo_video, or clear_promo_video, leaving alternatives implicit.

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