Raw Request

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: there is no method argument, GET/POST is decided by the endpoint, and --yes is added uniformly, meaning the audit-whitelist confirmation is bypassed for endpoints outside the whitelist. That is exactly the kind of risk context an agent needs for a privileged mutation-capable entry point. It does not address auth/profile behavior or failure handling, keeping it below a 5.

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?

Purpose is front-loaded, the mechanism explanation follows, and the concrete example anchors the end. Sentences are dense but each carries information; minor redundancy between the prose and the example keeps it from a 5.

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?

An output schema exists, so return values need not be explained, and all six parameters are schema-documented. The description supplies the fallback framing, the CLI mechanism, and the safety caveat, which is adequate for a raw passthrough tool. It could say more about authentication/profile selection and error behavior for such a privileged gate.

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 documents all six parameters (body, host, port, scheme, profile, request). The description only restates that a body is passed via --json and that request is the endpoint, adding negligible meaning beyond the schema. Baseline 3 applies.

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 a specific verb and resource ('调用系统业务原始 API') and frames the tool as a fallback/privileged entry ('兜底，特权入口'), which separates it conceptually from the many typed siblings. It goes further by explaining the CLI format and giving a concrete example request. It stops short of naming which dedicated sibling to prefer (e.g. network_ssh_status for the example endpoint), so sibling differentiation is implied rather than explicit.

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 '兜底/特权入口' framing implies this should be used only when no dedicated tool covers the endpoint, and it adds a real safety instruction ('调用前请自己确认端点安全性'). However, it never states explicitly when NOT to use it or routes the agent to the specific typed alternatives, so the guidance remains implied rather than directive.

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