chatgpt_capabilities

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

With no annotations present, the description carries the burden of safety disclosure. '读取' clearly signals a read-only operation, and the explicit statement that it will not expand submenus preempts a common side-effect concern. It does not describe output shape or other side effects, but for a read-only composite this is strong disclosure.

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 tight sentences with no filler: the first lists what the tool reads, the second gives usage and a key limitation. Information is front-loaded and every clause earns its place.

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 annotations, no output schema, and only a minimally documented parameter, so the description must be self-sufficient. It covers the returned fields, when to use, and a limitation, but it leaves historyLimit unexplained and does not describe how the composite result is structured. It is adequate but has clear gaps.

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 schema has 0% description coverage and the tool description never mentions historyLimit. '少量可见历史摘要' hints at a limited history summary but does not explain that the parameter controls the number of history items or how the default/min/max apply. The parameter name and constraints are self-evident, but the description does not add the needed meaning.

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 ('读取' / read) and enumerates the exact resources returned: current mode, model, thinking strength, temporary state, and a small visible history summary. It also distinguishes itself from sibling status/selection tools by noting it aggregates multiple state reads and does not expand submenus.

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 says to use the tool 'when a comprehensive pre-check is really needed' and to avoid calling multiple status tools in sequence, which names the main alternative. It notes the tool does not expand model/thinking-strength submenus, but it does not name a specific sibling tool or explicitly state 'do not use when only one status is needed.'

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