restart_if_stale

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

The description adds significant behavioral context beyond the annotations: 'Bounded mutation', no-op with a reason, immediate return with delayed effect, the need to poll runtime_info, and refusal when unsupervised. This fully characterizes the tool's side effects and timing.

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?

Three sentences deliver complete operational guidance with no filler. The first sentence front-loads the most important classification ('Bounded mutation') and the exact trigger condition, followed by return behavior and constraints.

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?

Given no parameters and no output schema, the description covers all essential context: what the tool does, when it acts, when it does nothing, what the caller experiences, how to observe the outcome, and a safety precondition. Nothing critical is missing.

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?

There are zero parameters and the schema is an empty object with 100% coverage, so the description has no parameter burden. It still adds relevant semantic context about the action's bounds and conditions, which is more than sufficient for a parameterless tool.

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 states a specific action ('Restarts the worker') and precise triggering condition ('only when it demonstrably serves a stale build'), with concrete detection criteria. It clearly distinguishes this tool from siblings like runtime_info, machine_status, and self_update.

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?

It explicitly says when to invoke the tool (when a stale build is demonstrated), when not to (no-op when fresh), and what to do after (poll runtime_info for the new worker). It also names an exclusion condition ('Refuses when unsupervised').

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