submit_node

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

Without annotations, the description carries the full burden of behavioral disclosure. It reveals that the tool blocks until ancestors finish and is metered (likely incurs cost or usage tracking). However, it does not disclose side effects on the node (e.g., state changes), error handling, cancellation behavior, or idempotency—important for a long-running blocking operation.

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 exceptionally concise: two short sentences that front-load the primary action and immediately provide critical behavioral constraints (blocking, metered). Every word carries weight, no redundancy or fluff.

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 tool's complexity (blocking, LLM execution, metered) and lack of output schema, the description is incomplete. It omits details about return value format (what does 'completed node' contain?), error scenarios (ancestor failure, timeout), and concurrency limits. Siblings like retry_node and interrupt_node imply complementary features but are not cross-referenced.

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 input schema already contains descriptive parameter comments (100% coverage), so the description adds minimal value for parameters. The only extra insight is the implicit context that 'nodeId' refers to nodes in a tree that can have ancestors, but this is not stated explicitly for parameters. Baseline 3 is appropriate.

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 action: 'Run the LLM on a node and return the completed node.' It uniquely distinguishes from siblings like create_node (creation only), get_node (retrieval), retry_node (retry), and interrupt_node (interruption). The verb 'submit' combined with 'run' on a node makes the purpose specific and unambiguous.

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 provides a key context: 'Blocks until ancestors finish; metered.' This hints at when to use (when you need to run a node after its dependencies) but does not explicitly state when not to use or mention alternative tools. No guidance on prerequisites or common pitfalls, leaving room for ambiguity.

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