chatgpt_capabilities

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

With no annotations, the description carries the full burden. It transparently describes the read-only aggregate behavior, what data is captured, and explicitly notes a limitation (does not expand submenus). It also implies efficiency benefits. It could state no-side-effects more explicitly, but the read verb and context suffice.

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?

Two sentences are front-loaded: first states the function, second states the usage and limitation. Every clause adds value with no repetition or fluff.

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?

The tool has no output schema and a single configurable parameter, so the description must compensate. It covers purpose, usage, and scope well, but omits the historyLimit semantics and any return structure. For a status-combining tool, this is adequate for selection but leaves gaps for correct invocation with parameters.

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 only parameter, historyLimit, is not mentioned in the description, and schema coverage is 0%. The schema provides numeric constraints but no semantic meaning. The description's reference to '少量可见历史摘要' is too vague to convey that historyLimit controls the amount, leaving the agent to guess the parameter's role.

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 uses a specific verb ('一次读取' / read at once) and clearly enumerates the resources: current mode, model, thinking strength, temporary state, and a visible history summary. This aggregates several sibling status tools, clearly distinguishing it from individual list/select tools like chatgpt_list_modes or chatgpt_status.

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?

It explicitly states when to use: '用于确需综合预检时，避免连续调用多个状态工具' (when a comprehensive pre-check is needed, to avoid multiple status calls). It also gives an exclusion: '不会展开模型或思考强度子菜单' (does not expand submenus), implying when not to use it and directing toward the list tools.

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