train_compliance

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

With no annotations provided, the description carries the full burden. It discloses key side effects: the report is written to the dataset version ('报告写训练集版本') and severe findings block training submission ('严重级发现阻断训练提交'). It also explains the action variants' behavior (scan writes, gate asserts, mark sets provenance). It does not mention permissions, reversibility, or rate limits, but the essential behavioral traits are covered.

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 a single dense sentence with semicolon-separated clauses, front-loaded with the primary purpose ('训练数据合规扫描'). It packs the three risk categories, detection method, report behavior, blocking rule, and provenance marking without wasted words. Efficient and structured.

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 5 parameters, 2 enums, and no output schema, the description covers the main behaviors: what is scanned, how detection works, what the report contains, the blocking condition, and the provenance action. It does not detail error handling or return format, but those are not required given the absence of an output schema and the complexity level. The description is sufficient for an agent to invoke it 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?

Schema description coverage is 100%, so the baseline is 3. The description adds some context by linking actions to behaviors (e.g., 'scan 扫描+写版本' vs 'gate 只断言') and clarifying that provenance is used for source marking. However, this mostly repeats what the schema already states (e.g., 'mark 必填'), so the added value is marginal.

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 tool's purpose: '训练数据合规扫描' (training data compliance scan) and enumerates three risk categories (PII, sensitive fields, enterprise terms) with a specific detection method (redactor whitelist). It is a distinct operation compared to siblings like train_dryrun or train_doctor, which focus on other aspects of training.

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 implies usage (scan before training submission) but does not explicitly state when to prefer this over alternatives or when not to use it. It explains the three actions (scan/gate/mark) in the description but does not provide conditions like 'use gate for read-only assertion' – that is left to the schema's enum descriptions. No alternative tools are named or excluded.

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