blockrun_realface

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

Annotations only indicate the tool is not read-only, but the description adds substantial behavioral context: multi-step liveness enrollment, free vs. paid actions, H5 link expiration (~120s), polling for active status, and privacy guarantees that BlockRun does not store face/liveness data. This goes far beyond what annotations provide and does not contradict them.

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 long, but every section earns its place given the multi-step workflow. It is front-loaded with the core purpose, uses bullet-style sections for actions, and includes a typical flow that converts complex sequencing into an easy-to-follow pattern. The privacy note is a useful closing detail rather than fluff.

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 complex paid/free multi-step tool with no output schema, the description is remarkably complete: it explains init/status/enroll/portrait/list, costs, liveness requirements, expiration behavior, model compatibility, and expected results (ta_xxxx asset ids). An agent has enough context to invoke all five actions correctly and route to blockrun_video afterwards.

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 the schema already covers all parameters, the description adds critical semantics: which actions require which parameters, group_id can refresh an expired link, image_url must be the same person as the liveness check, and action-specific behavior. It also clarifies that name is required for init, enroll, and portrait, which is not obvious from the top-level schema alone.

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 a specific verb-resource statement: enrolling a real person's face as a BytePlus RealFace asset and using it to drive Seedance 2.0 video. It clearly distinguishes the tool from siblings by explaining what it feeds into (blockrun_video real_face_asset_id) and separating real-person vs. portrait enrollment.

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 gives explicit when-to-use guidance for each action, including when to use portrait versus the liveness flow for real people. It also states model compatibility constraints (seedance-2.5 does not accept ta_ assets) and provides a typical end-to-end flow, making it easy for an agent to select and sequence calls correctly.

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