stop_check

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

With no annotations, the description carries the full load and does it well: it declares the tool is a hard gate ('必须调我'), specifies the three conditions under which it withholds advice, explains why the stakes are accidents rather than rework, and describes the shape of the response. It does not say whether it is purely a read or whether results are logged/cached, nor anything about latency — minor gaps only.

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?

Front-loaded with the gate rule, then the invocation conditions, then the rationale, then a concrete example — a sensible ordering. Slightly dense with some restatement (the 'these three get no advice, ask me first' idea appears twice) but every block contributes; nothing is padded.

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?

There is no output schema, so the description must explain the return values, and it names them all including the risk_class vocabulary and the stop-point guidance. For a zero-required-param classifier gate, an agent has everything needed to decide to call it and to interpret the answer.

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 coverage is only 33% (only query is documented), so the description must compensate, and it does: it explains that you pass category and symptom, or alternatively one colloquial sentence, and gives a worked example using query=「摸冰箱外壳有点麻手」. It does not state what happens if all three optional params are omitted or how category_id and symptom_id pair up when both are supplied.

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?

States a specific role: a mandatory safety gate invoked before any DIY hands-on advice, and enumerates what it returns (risk_class with gas/electric/water/height/none, must_stop_before_diy, stop points, who to contact, rough cost). The 'before giving DIY advice' framing distinguishes it from diagnose/fix_plan without naming them, so an agent can place it in the workflow.

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?

Explicitly lists the three mandatory invocation cases (gas smell or gas pipes/valves; live electrical work, numbness, tripped breakers, smoking outlets; water that may reach circuitry) and states that these three get no advice until this tool is called. That is an unambiguous when-to-use rule plus an exclusion, which is the strongest form of routing guidance.

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