manage_instance

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

With no annotations, the description takes on full disclosure burden. It reveals key behavioral details: reboot stops/starts preserving GPU priority, recycle destroys and recreates from fresh image pull. It also documents endpoint patterns. It doesn't mention auth or rate limits, but for the core actions it is transparent.

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?

Structured with a clear summary line, bullet points for actions, and relevant examples. Every sentence adds value, and the formatting is easy to scan. No redundant content.

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?

The description is comprehensive for a multi-action tool, covering all action types and their differences. Output schema exists, so return value explanation is unnecessary. Minor gaps include no explicit mention of error conditions or prerequisites, but the examples and action semantics make it largely complete.

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 0%, so the description must compensate. It explains the action enum values, notes that label is required when action='label', and provides examples showing parameter usage. instance_id is self-explanatory. This is adequate coverage for the three parameters.

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's function: 'Control instance state' and enumerates specific actions (start/stop/label/reboot/recycle). It distinguishes from sibling tools like destroy_instance and create_instance by focusing on state management, and provides concrete action definitions.

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?

Provides clear guidance on each action's semantics, including when to use reboot vs recycle (preserves GPU priority vs fresh image pull). Includes examples for common usage. However, it doesn't explicitly contrast with alternative tools like destroy_instance for permanent deletion, which would strengthen it.

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