recover_current_task

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

With no annotations, the description carries the full behavioral burden, and it only discloses that recovery is limited to navigation and will not recreate the browser or session. It says nothing about permissions, side effects, failure modes, or what state is left behind — and the exclusion of session recreation sits in direct tension with a parameter literally named renew_session, which the description never resolves.

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 clause with no waste and the scope caveat front-loaded, so it is structurally fine. The terseness crosses into under-specification: the sentence is short because information is missing, not because it is efficiently packaged.

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 recovery tool with three undocumented flags, no annotations, and no output schema, an agent needs to know what each flag toggles and what recovery leaves in place. The description covers only the outer boundary and leaves the operation itself opaque.

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 three boolean parameters (renew_session, recover_read_worker, cancel_hung_play_wait), so the description must compensate and instead adds nothing. Worse, its "no browser/session recreation" claim appears to conflict with renew_session, leaving an agent unable to tell what that flag actually does.

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?

"One normal navigation recovery of an observed task" identifies a verb (recover) and object (current task), so the general purpose is inferable. But "observed task" and "normal navigation recovery" are internal jargon that is never defined, and the description does nothing to distinguish it from near-neighbours like restore_owned_window, recover_owned_exam_worker, or inspect_current_task.

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 clause "no browser/session recreation" implies a boundary (don't use this when a full session rebuild is needed), which is the only routing hint present. There is no positive statement of when to call it, what precondition triggers it, or which sibling to use instead.

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