blockrun_realface

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

The description fully discloses behavioral traits: multi-step flow with liveness check, costs (FREE vs $0.01 USDC), H5 link expiration (~120s), privacy note about not storing data. Since no annotations exist, the description carries the full burden and meets it comprehensively, covering safety, statefulness, and payment requirements.

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 well-structured with clear sections: main purpose, action list, typical flow, privacy note. It is front-loaded with the core verb-resource. However, it is somewhat lengthy due to detailed action explanations; a slightly more concise format could improve efficiency, but the structure is logical and each sentence 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?

Given the complexity (multi-step, paid, requires external liveness check), the description is remarkably complete. It covers the full workflow, prerequisites, costs, expiration, and privacy. No output schema is present, but the return values (asset id) are implied. The description leaves no critical gap for an AI agent to understand and execute the tool correctly.

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?

Although schema coverage is 100%, the description adds significant value beyond parameter names and types. It explains which parameters are required for each action (e.g., 'name required for init and enroll', 'group_id for status and enroll'), clarifies the format of image_url, and describes the role of agent_id for budget tracking. This contextual guidance is crucial for correct invocation.

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 core purpose: enrolling a real person's face as a RealFace asset for use in Seedance 2.0 video generation. It distinguishes from sibling tool blockrun_video by specifying that real_face_asset_id is used there, and explains the multi-step flow. The verb 'Enroll' and resource 'RealFace asset' are specific and unambiguous.

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 explicit context for use: it is for generating video of a specific real person via Seedance 2.0, contrasting with generic seed images. It outlines the four possible actions (init, status, enroll, list) and when each is appropriate, including a typical flow. While it does not explicitly state when NOT to use this tool, the guidance is clear enough for an AI agent to select it correctly.

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