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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is partly covered. The description adds two facts the annotations cannot: the precise verdict semantics (wall-clock budget vs. due window) and a cost guarantee via 'Not metered', implying the routine sweep is quota-neutral even though it writes verdicts. Idempotency is only hinted at through 'MISSED once per due window'.

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, front-loaded with the action, then compact definitions of each verdict. The opening colon-clause slightly restates the title, but it earns its place by introducing the verdict list; the closing cost note is short and load-bearing.

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 zero-parameter, side-effecting sweep with no output schema, the description explains what conditions produce verdicts but not what the call returns — whether it lists affected runs, counts, or nothing at all. It also leaves invocation cadence and repeat-call behavior implicit, which is the main remaining gap for an agent deciding when to trigger it.

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 tool takes zero parameters and the schema is an empty object, so there is nothing for the description to disambiguate. The baseline for a no-parameter tool is 4, and nothing here contradicts or muddies the 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 gives a specific verb and resource ('Run the watchdog sweep') and defines the two verdict types it can emit, STALLED and MISSED, with their triggering conditions. This distinguishes it from siblings like checkpoint, verify_now, and start_run, which appear to be the inputs the sweep evaluates. It stops short of naming those siblings explicitly as alternatives.

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 word 'sweep' and the phrase 'once per due window' imply a periodic, scheduled invocation, but the description never states when an agent should call this versus verify_now or list_verdicts, nor any when-not conditions. Usage is inferable from context rather than stated.

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