Retrieve nodes for a specific run in append order, paginated with limit and cursor. Use this to inspect agent execution steps or debug run behavior by querying node sequences.
List nodes for a run in append order (paginated).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| cursor | No | opaque pagination token from previous response next_cursor; pass through unchanged | |
| run_id | Yes |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already supply the safety profile (`readOnlyHint: true`, `openWorldHint: true`). The description adds value by disclosing 'append order' and 'paginated', which are behavioral details not present in the annotations; however, it does not clarify what a 'node' is, what data is returned per node, or whether failures are included.
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 short sentence that is front-loaded with the action, resource, and key behavior. It is economical and wastes no words, though the phrasing is so brief that some informational gaps (purpose clarity and parameters) bleed into other dimensions.
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 paginated read tool the description covers the two main behavioral aspects: ordering and pagination. It is missing a light definition of what qualifies as a node and any mention of the return shape, but the annotations carry the safety burden and the parameter name `run_id` is self-explanatory.
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 description coverage is only 33%, with `run_id` and `limit` having no descriptions in the schema; the description must compensate but does not. The word 'paginated' hints at `limit`/`cursor`, but nothing explains how `run_id` identifies the run or how ordering relates to appended nodes.
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 states a specific action ('List nodes') with a clear resource ('for a run') and scope ('append order', paginated). It is understandable on its own, but it does not differentiate from the look-alike sibling `invariance_list_nodes`, which leaves an agent unsure which of the two near-identical names to select.
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 no guidance about when to choose this tool over alternatives. The sibling set contains `invariance_run_llm_calls`, `invariance_run_operational_graph`, `invariance_list_nodes`, and `invariance_node_write`, and nothing here clarifies what this tool returns compared to those or when one should be preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.