Start, stop or restart a Wiro agent

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

Annotations cover safety (readOnly=false, destructive=false, idempotent=false), and the description adds substantial context beyond them: start charges nothing by itself, stopping does not pause the plan and it will auto-restart in 30 days, the change is asynchronous, and refused starts return actionable guidance. This is rich behavioral disclosure that the annotations alone would not provide.

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?

The description is front-loaded with the core verb+resource and then layers billing, async, and permission context in ordered sentences. It is dense but each sentence carries distinct, useful information; a slightly tighter phrasing of the billing caveat could reduce length without losing value.

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?

An output schema exists, so return values need not be explained, and the description still covers the async completion path (wait_seconds or nextAction), refusal handling, and permission requirements. For a 3-parameter state-changing tool, an agent has everything needed to invoke it correctly and interpret the result.

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 coverage is 100%, so the schema already documents action, agent_guid, and wait_seconds. The description nonetheless adds semantic value: it explains the billing precondition on start, the background nature of the change, and the nextAction follow-up pattern tied to wait_seconds. It stops short of explaining edge cases like restarting a stopped agent, keeping it just under a 5.

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 opening sentence names the resource (deployed agent) and the three specific actions (start, stop, restart), then defines what each one does in concrete terms ('restart reloads the agent with its current settings'). It is clearly distinguishable from siblings like manage_agent_billing, which it explicitly delegates billing cancellation to.

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 states when to use each action, names the alternative for the related-but-different need ('cancel the plan with manage_agent_billing to stop paying'), and explains the permission model for team agents (team admin or deployer) along with the read-only fallback (get_my_agent) for other members.

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