operation_control

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

No annotations are supplied, so the description carries the full disclosure burden, and it omits nearly all of it: whether cancel is irreversible, what state the operation lands in afterwards, whether recover destroys the existing browser session, or what permissions are needed. Only one behavioral detail surfaces — that continue can extend budget — which is far short of what a state-mutating control tool needs.

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 semicolon-delimited line with action name first and meaning second, which scans well for an agent matching an action to an effect. No filler; the only cost is that the compact list format leaves no room for the conditions and constraints noted above.

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?

For a four-parameter, multi-mode control tool with no annotations, the description should map parameters to actions and state the effect of each mode. It does neither for the three optional parameters, and an output schema existing only relieves it of explaining return values, not of explaining control semantics.

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% across four parameters, so the description must compensate and largely does not. It documents the effective values of `action` (a genuine gain, since the schema declares no enum), but operation_id, additional_seconds and additional_requests are only obliquely gestured at by '可追加预算' — there is no statement of which actions require an operation_id or how the two budget parameters interact.

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 enumerates five concrete action verbs (cancel, continue, resume, show, recover) and what each does to an in-flight operation/browser session, so the resource and effects are identifiable. It does not explicitly differentiate itself from the sibling operation_status, leaving the control-vs-inspect boundary implicit.

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?

Per-action conditions are given for two actions ('continue' is for interrupted or budget-exhausted searches; 'resume' is for when a manual step is done), which is real routing guidance. However cancel/show/recover have no stated preconditions, and the description never says when to call this instead of operation_status or what to do if the operation is unknown.

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