blockrun_realface

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

The description goes far beyond the sparse annotations (all false) by disclosing costs (FREE vs. paid $0.01 USDC), the mandatory liveness check, the H5 link expiration (~120s), the multi-step enrollment process, and a privacy statement. It also explains that enrollment is not a single step and that group_id can be reused to refresh an expired link. This fully compensates for the lack of annotation detail.

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 lengthy but well-structured: a clear introductory sentence, an explanatory paragraph about RealFace assets, a bulleted list of actions with costs and requirements, a numbered typical flow, and a privacy note. Every section delivers essential information, and the front-loading makes the purpose immediately clear. No filler or repetition.

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 five actions, no output schema, and minimal annotation signals, the description is remarkably complete. It covers return values (ta_xxxx ids), prerequisites (liveness, public image URL), expiration behavior, model compatibility constraints, cost implications, and a concrete usage example. It leaves no major gaps for an agent to select and invoke this 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 the schema already provides per-parameter descriptions (100% coverage), the description adds critical semantics: it explains that group_id must come from init, that image_url must be a clear front-facing photo, that name is required for init/enroll/portrait, and that agent_id is for budget tracking on enroll. It also clarifies that group_id is not used by portrait, which is not obvious from the 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 states the tool's core function with a specific verb ('Enroll') and resource ('a real person's face as a BytePlus RealFace asset'), and explicitly distinguishes it from sibling blockrun_video by explaining that the asset is later consumed by that tool. It also differentiates between real-face enrollment (init/status/enroll) and AI character enrollment (portrait), leaving no ambiguity about what the tool does.

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?

Provides explicit when-to-use guidance: which models accept ta_ assets, when to use portrait vs. the liveness flow, and the exact sequence of actions in a typical flow. It also names the alternative (blockrun_video) and clarifies that this tool is for creating the asset, not generating video.

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