打开额度续跑控制中心

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that the tool displays a clickable UI within Codex and requires pre-fetched tasks, which is useful context. However, it does not disclose what happens when elements are clicked, whether the display is modal or transient, or how the passed tasks are rendered—behavioral details that could matter to an agent.

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: the first states the tool's function, the second gives the key prerequisite. It is front-loaded, concise, and every sentence contributes useful information. No filler or redundant restating of the tool name.

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 is simple and read-only, but the description still leaves an entire parameter ('safetyDelaySeconds') unexplained and gives no detail about the 'tasks' object shape. Since there is no output schema, the description carries the burden of explaining behavior and inputs. It covers the prerequisite but misses enough operational detail that an agent cannot fully reason about how to set 'safetyDelaySeconds' or what the control center will do with the tasks.

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 compensate for both parameters. It does explain that 'tasks' should contain candidate tasks obtained from Codex's task list, which adds some meaning beyond the schema. However, it does not describe the required fields (id, title), the meaning of 'isCurrent', or the behavior of 'safetyDelaySeconds', which is a meaningful control parameter with default 120 and range 30-3600. This partial compensation is insufficient for a 0%-coverage schema.

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 states a specific action ('显示可点击的额度续跑控制中心') and the context ('在 Codex 内'), clearly identifying it as a UI-display tool rather than a data-mutation tool. It is distinguishable from the quota_resumer_* siblings because it is the only one focused on rendering a clickable control center in Codex. It loses one point because the meaning of '额度续跑控制中心' remains jargon-heavy and is not further explained.

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?

The description gives an explicit prerequisite: before calling, use Codex's task list capability to fetch candidate tasks and pass them as 'tasks'. This provides clear when-to-use context. It does not mention alternatives or exclusions, but for a UI-display tool this is a reasonable clear context without needing much negative guidance.

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