打开同济 AI 积分面板

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

Annotations already declare readOnlyHint=true, destructiveHint=false and idempotentHint=true, so the safety profile is covered. The description does add real context beyond them by disclosing that the invocation produces a UI artifact ('打开可交互面板') and enumerating which fields are shown, but it says nothing about what happens on failure, whether the panel blocks, or how the output is delivered returning to the caller.

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?

A single well-formed sentence with the payload front-loaded and no filler. It loses a point because cramming the fixed word '今日' into an otherwise general-purpose panel description creates ambiguity rather than compactness.

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?

With no output schema, the description usefully enumerates the fields the panel surfaces, which is the right thing to do. But for a tool with an optional range enum and a UI side effect, it leaves the period-scoping behavior and the delivery mechanism unexplained, so an agent cannot call it optimally without guessing.

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?

There is one parameter with 0% schema description coverage, and the enum values (today/yesterday/7d) are undocumented in prose. Worse, the description hard-codes '今日积分消耗', which subtly contradicts the fact that range accepts yesterday and 7d, so an agent reading the text could infer the period is fixed to today and never set the parameter.

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?

A clear verb-and-resource statement: it names the concrete data surfaced (plan balance, credit consumption, actual token usage, login status) and adds that it opens an interactive panel. It is distinguishable in substance from a plain usage-fetch tool, but it never names the sibling get_tongji_usage, so the agent must infer the split between 'open panel' and 'get numbers' on its own.

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?

Usage is only implied: the phrase '打开可交互面板' hints this is the interactive/dashboard path versus a pure data fetch, but there is no explicit when-to-use, when-not-to-use, or named alternative. No prerequisites (login state, account binding) are stated, even though tongji_login exists as a sibling that may need to run first.

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