preview_install

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

No annotations are provided, so the description carries the full burden. It clearly states the tool is a non-destructive preview, shows what changes would be made, and describes the return structure. It does not mention authentication or rate limits, but these are less critical for a preview tool. The async nature is hinted through the example but not explicitly stated.

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 well-structured with a summary, parameter docs, return block, and example. It is not overly verbose; each section adds value. Slight improvement possible by removing the example's explicit wait_for_task import, but overall efficient.

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 annotations and moderate complexity, the description covers the tool's purpose, parameters, return schema, and a usage example. It connects to sibling tools (install_package, get_preview_result) implicitly through the workflow. It could explicitly mention the async nature and error handling, but the provided information is largely sufficient.

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 description adds significant meaning beyond the schema: it explains the purpose of each parameter (adom: ADOM name, package: optional, devices: list of dicts with name and vdom). This compensates for the 0% schema coverage. However, there is a minor contradiction: the schema marks package as required, but the description says 'optional, preview device settings if None', which could confuse agents.

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 purpose: to preview installation changes before applying, without actually installing. It uses specific verbs and resources (preview, installation changes, devices) and distinguishes itself from sibling tools like install_package and get_preview_result through the description and example workflow.

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 explicitly says 'Use this to verify changes before deployment', indicating when to use. The example workflow further clarifies the sequence (preview, wait for task, get results). However, it does not explicitly exclude alternatives or state when not to use, which would improve guidance.

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