drain_replica

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

No annotations provided, so the description fully discloses behavior: it refuses, explains why, and notes dry_run reports unavailability. The [WRITE][risk=high] tag adds risk context. This is complete transparency.

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 a bit verbose but well-structured: a clear warning banner, a concise explanation of unavailability, an alternative, and an args list. Every sentence earns its place, though it could be tightened slightly.

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 that this is a deliberate stub/refusal tool, the description covers all necessary context: why it exists, what it does, what the alternative is, and how parameters behave. No output schema is needed since the tool always refuses except dry_run.

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 0%, but the description explains all five parameters with meaningful purpose: application (name), deployment (name), replica_id (from replica_list), dry_run (preview), and target (config default). This compensates fully for missing schema descriptions.

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 tool drains one replica but immediately clarifies it's NOT available over Ray's REST API and refuses with a teaching error. It distinguishes itself from siblings by naming the alternative (scale down) and explaining the limitation.

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 provides when-not-to-use and alternative: 'To retire surplus replicas, scale the deployment down — the controller drains them gracefully.' Also mentions that draining is Python-API only, guiding the agent away from this tool.

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