recover_owned_exam_worker

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

With no annotations, the description must carry behavioral disclosure, and it does establish the two most important traits: the operation is read-only and it must not re-issue a save (idempotency safety). It stops short of stating what the fence observes, whether it acquires or releases ownership, or what the caller should expect on success versus a dead worker.

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 compact clause pair with zero padding, and the situational trigger is front-loaded ahead of the caution. The density of unexplained jargon ('liveness fence') costs a point against genuine front-loaded clarity.

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?

No output schema exists, so the description is the only source of return-value information, and it says nothing about what a fence check yields or how the agent should act on the result. For a zero-param recovery tool in a 100+ tool surface, that leaves the caller guessing at the outcome contract.

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 zero parameters with 100% coverage, so the baseline is 4. The description adds nothing parameter-related, but nothing is required of it here; the worker identity must be implicit in server state.

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 verb+resource combination (recover_owned_exam_worker) is strengthened by 'after a timed-out batch', which tells the agent this is a post-timeout recovery step. But 'read-only liveness fence' is internal jargon that does not clearly state what the tool actually does or returns, and it does not distinguish itself from the several recover_* siblings (recover_current_task, recover_graded_parallel_account, recover_terminal_media_account).

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?

'after a timed-out batch' gives a concrete trigger condition for use, and 'never replay a save' is an explicit prohibition. However, there is no guidance on when to prefer this over the other recover_* tools or what to do if the fence reports an unhealthy worker, so the routing decision is only implied.

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