List nodes

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

The readOnlyHint annotation already establishes no side effects, and the description aligns with that by saying 'List' and requiring only nodes.read. It adds useful context about returned data and auth requirements, though it does not describe pagination behavior or failure modes.

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 single, concise sentence that covers purpose, output fields, and required permission. There is no redundant or filler content, and parameter descriptions are similarly tight.

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 list operation with no required parameters and no output schema, the description adequately indicates what is returned and what permission is needed. It does not specify the exact response shape or pagination metadata, but the main fields are listed and the operation is clearly scoped.

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?

All four parameters have descriptions that go beyond the bare schema: page, per_page, search, and detail are each explained. The detail description explains summary vs. full but includes unrelated examples about servers and eggs, slightly reducing precision for a node-specific tool.

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 lists wings nodes attached to the panel and enumerates the returned fields (location, public URL, SFTP endpoint, memory/disk allocation limits). It is distinct from sibling tools such as list_servers, list_locations, get_node, and get_node_resource.

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 gives the required permission scope ('nodes.read') and indicates a read-only collection operation. It does not explicitly contrast with get_node or get_node_resource, but 'List' plus the specific node resource makes the intended usage clear.

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