get_job

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds meaningful async semantics — that the dispatching tools answer before the work completes and that status must be polled to a terminal `finished` flag — which is real behavioral context beyond the annotations. It does not mention timing, retry limits, or error behaviour if the task_id is unknown.

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?

Front-loaded with the outcome question, then the polling protocol. The closing sentence about never checking is slightly motivational rather than instructional, but it reinforces the polling contract and does not bloat the definition materially.

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?

There is no output schema, so the description carries the burden of naming the fields an agent must read — it does this for `finished` and `succeeded`. What is still missing for a polling tool is terminal-state handling (e.g. failure detail, whether the job record survives until polled, or what happens after several polls).

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 100% and the sole parameter's schema text already explains that task_id comes from undo_transaction, verify_tree, reindex_search or run_report. The description restates the same dispatching set, so it adds little beyond the schema; baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb and resource ('check whether a background job has finished, and whether it worked') tied to a named object ('task_id'). An agent can distinguish this from list_jobs because the description frames it as polling a single dispatched job for its terminal state, not enumerating jobs.

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?

Explicitly names the operations that dispatch work (undo, verification, import, reindex) and the exact usage loop: 'Poll this until `finished` is true, then read `succeeded`.' It even states the failure mode of not using it ('leaves you assuming an outcome you have not seen'), so when-to-use and when-not-to-skip are both covered.

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