Start the worker

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

Annotations already indicate mutating (readOnlyHint=false), external side effects (openWorldHint=true), and idempotency (idempotentHint=true). The description adds meaningful nuance beyond these: it discloses the conditional behavior (only acts when tasks pending and scheduler allows) and the no-op scenario when another process owns the queue. This enriches the agent's understanding of when side effects actually occur.

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, directly front-loaded with the primary action. Each clause earns its place: the action, the conditional triggers, and the ownership caveat. No filler, no redundancy.

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 tool with no parameters and no output schema, the description is nearly complete. It covers what it does, when it acts, and when it is a no-op. Subtle points like asynchronous execution or post-condition state are not mentioned, but these are minor given the annotations and context.

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 has zero parameters and an empty schema (100% coverage). Per the rubric, a baseline of 4 is appropriate when there are no parameters to document. The description doesn't need to add parameter details, and it doesn't.

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 clearly states the action: 'Start (or resume) the background worker in this process.' It identifies the resource (background worker) and the scope (this process), and adds a distinguishing condition (no-op if another process owns the queue). While it doesn't explicitly name sibling tools like queue_resume, the 'in this process' qualifier effectively differentiates it from process-wide queue operations.

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 description provides context on when the tool actually acts: 'It only acts when tasks are pending and the scheduler allows it. No-op if another process owns the queue.' This tells the agent the conditions under which it should expect an effect. It does not explicitly compare with queue_resume or queue_pause, but it gives enough guidance for the current process context.

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