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

The description discloses that the operation is asynchronous and returns a generation_id, which is key behavioral information not available in annotations (annotations only have readOnlyHint=false and openWorldHint=true). It also mentions the starting price, which is a side effect (cost) and useful context. This adds value beyond the schema and annotations, though it doesn't detail error handling or side effects like potential data loss, but for a generation tool, the async pattern is the main behavioral trait.

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 concise and front-loaded with the core purpose ('Replace characters in videos'), then provides critical operational details (cost, async behavior) in a single additional sentence. Every word earns its place, with 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?

Given the tool's complexity (asynchronous, 4 params, no output schema), the description provides the essential guidance needed: async flow and the follow-up step. It does not describe the return structure (e.g., what 'generation_id' looks like), but the schema covers input parameters thoroughly. The lack of an output schema is acceptable since the description directs users to call get_generation. It's nearly complete, but could mention error handling or rate limits, but those are not critical for a first call.

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?

Since schema description coverage is 100%, the schema already documents all parameters (video, character_image, prompt, resolution) with descriptions. The tool description does not add additional meaning beyond the schema, such as formatting details or examples. However, it does add slight context by mentioning 'from $0.75' which could relate to cost for processing, but that's not parameter-specific. Baseline 3 is appropriate as the schema covers the semantics.

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 clearly states the action ('Replace characters in videos') and the resource (videos). It distinguishes from related siblings like ai_face_swap_video by focusing on character replacement, though it does not explicitly name the sibling. The purpose is clear and specific enough for an agent to understand the tool's core function.

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 provides essential usage context by noting the asynchronous behavior and the need to poll get_generation until completion, which is critical for correct invocation. However, it does not specify when to use this tool over others (e.g., ai_face_swap_video or ai_head_swap) or when not to use it. The 'when' is implied by the tool's function, but no explicit alternatives or exclusions are given.

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