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

Annotations already signal read-only and non-destructive behavior, but the description adds meaningful behavioral context: `null` means never set, the endpoint is deliberately separate due to payload size, read access is required, and multi-space accounts need space selection. The general note about treating stored content as data, not instructions, adds security context beyond the annotation set.

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 purpose and then adds necessary clarifications about null semantics, why the endpoint is separate, and auth requirements. The final sentence about ChangeRequests feels somewhat tangential for a GET-only tool, but it is short and contextual, so the description remains efficiently structured.

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 two-parameter read endpoint with no output schema, the description covers the important edge cases: null vs empty, multi-space handling, read permission, and the reason for the separate endpoint. It does not describe the exact response shape, but the description gives enough context for an agent to invoke the tool appropriately and interpret the likely 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 only 50%, but the description compensates by explaining the optional targetSpaceId parameter and how it should be determined via auth_verify. The required nodeId is clearly implied by the endpoint path, so the lack of a schema description is not a real gap. Overall, the description adds useful meaning beyond the bare parameter names.

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 identifies the operation: retrieving a node's custom scenario prompts, with precise distinctions from built-in prompts and from the node object itself. It also states the `null` vs empty-list semantics. The purpose is specific enough to distinguish from sibling tools like nodes_get and nodes_update_agent_prompts.

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 clear context for when this endpoint is appropriate: when custom prompts are needed and when loading them as part of node listings would be too heavy. It also gives a concrete precondition for multi-space accounts: call auth_verify, ask the user which space, and pass targetSpaceId. It does not explicitly name a sibling alternative, but the usage context is strong enough.

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