retry_node

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

With no annotations, the description carries full burden. It discloses that the tool clears error state and re-runs generation, and mentions the force parameter for expand nodes, but does not explain other behaviors like what happens if the node is not in error state or what output is expected.

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 two well-structured sentences with no unnecessary words. It is front-loaded with the core action first.

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 the absence of output schema and annotations, and 5 parameters with limited description, the description is too brief to fully guide an agent. It lacks details on parameter usage beyond force, return values, and error scenarios.

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 60%, and the description adds value for the force parameter by clarifying its use for expand nodes with children. However, it does not address prompt or modelId parameters, and the schema already describes mapId and nodeId.

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: 'Clear a node's error state and re-run its generation.' This is a specific verb-resource pair that distinguishes it from siblings like submit_node or interrupt_node.

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?

It provides some usage context by noting that retrying an expand node with children requires force=true, but it does not explicitly state when to use this tool versus alternatives or when not to use it.

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