corpus_export

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It does disclose that exports include a version number and HMAC signature, and that the action is logged as a corpus_export audit event, which is useful. However, it does not clarify whether the operation is read-only, whether it overwrites existing files, or any authorization requirements, leaving gaps for a tool with no annotation safety profile.

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 that efficiently conveys a large amount of technical detail. It is front-loaded with the main purpose ('训练语料导出三件套') and uses dashes and parentheses to list components, but the run-on structure reduces readability. It is concise but could benefit from clearer separation of the three components.

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 tool exporting multiple components, the description provides a strong high-level overview but lacks information on default behaviors (e.g., what happens with scope='default'), output format, or error handling. Since there is no output schema, the description does not explain return values, and terms like '六源聚合' and '脱敏' are mentioned without elaboration, leaving some ambiguity for an agent.

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?

The input schema provides 100% description coverage for all four parameters, so the description does not need to add parameter details. The description adds no extra information about parameters beyond what the schema already offers, which meets the baseline of 3 but does not exceed it.

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: exporting a training corpus composed of three components (rules, FDE methodology, labeled audit samples), with specific technical details like 27 numbered positions, verifiers three-bucket list, and six-source aggregation. This distinguishes it from siblings such as workflow_export or train_submit, which handle different export/training workflows.

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 no guidance on when to use this tool versus alternatives, nor does it mention exclusions, prerequisites, or context that would help an agent choose it. It merely describes what the tool exports, leaving the decision entirely to the agent's inference.

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