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

Annotations only mark it non-read-only and open-world; the description goes far beyond by disclosing the exact billing model (2 credits, charged whenever a report is produced including '照片不合格、无数据', not charged on param errors/unavailable kind/download failure/upstream failure), the photoUsable=false semantics, and a medical-disclaimer boundary. This is unusually rich operational context.

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?

Dense but front-loaded: purpose and return shape come first, then the kind source, then billing, then the failure/retake path and disclaimer. Each clause carries real information, though the billing sentence is long and could be split for faster scanning.

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 10-parameter mutation-style tool with no output schema, the description covers prerequisites, billing, failure modes, the photoUsable signal, and the non-diagnostic boundary. An agent has everything needed to call it and interpret the result.

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 100%, so the schema already carries the per-field documentation and the baseline is 3. The description still adds cross-tool meaning: kind must be a live type and its input form depends on inputMode from aicare_list_kinds, which is routing information absent from the schema itself.

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?

States a specific verb and resource ('提交一张照片做 AI 健康检测') plus the return shape (structured report with 体质辨识、健康评分、脏腑功能等), which lets an agent distinguish it from retrieval siblings like aicare_get_detection. It does not explicitly contrast itself with the overlapping aicare_tongue_diagnose sibling, so it falls short of a 5.

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?

Gives concrete prerequisites and routing: 'kind 取自 aicare_list_kinds 中 status=live 的类型', and it tells the agent what to do on failure (按 photoGuide 重拍). It stops short of naming when to prefer this over aicare_tongue_diagnose, so no explicit alternatives/exclusions.

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