管理同济 AI 浏览器登录

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

Annotations already declare readOnly=false, idempotent=false, openWorld=true and destructive=false, so the safety profile is covered. The description adds one genuinely non-obvious fact — '不会返回网站令牌' — which stops the agent expecting credentials back, but it says nothing about failure behavior, renewal side effects, or why renew is non-idempotent.

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?

One dense sentence with scope front-loaded, then the action inventory in enum order, then the return-value caveat. No filler, and the most decision-relevant clause (panel-only) comes first.

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 single-enum-parameter tool with no output schema, the description covers scope, all four actions, and the notable return-value limitation. It stops short of auth/prerequisite context, but the annotations plus the token caveat make it callable without further reading.

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 0%, so the description must carry the enum semantics — and it largely does, mapping each of the four enum values to a meaning (pair ↔ 配对浏览器助手, renew ↔ 立即续期, enable/disable ↔ 自动更新开关). Only minor gaps remain, such as what 'pair' requires on the user side.

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 names the concrete operations (pair, renew, enable/disable auto-update) and scopes them to the panel ('面板专用'), which lets an agent distinguish it from get_tongji_usage or tongji_check_update. The only ambiguity is that the tool is a four-action bundle under a 'login' name, so the single purpose is less crisp than a dedicated verb+resource tool.

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?

'面板专用' implies the caller context (panel operations) but gives no explicit when-to-use / when-not-to-use instruction and names no alternative tool. The action list implies which call to make, but prerequisites (e.g., must a browser assistant already be registered before 'renew'?) are left to inference.

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