Skip to main content
Glama
openl-tablets

OpenL MCP Server

Official
by openl-tablets
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

Get Trace Tree Nodes

openl_get_trace_nodes
Read-onlyIdempotent

Retrieve child nodes of a trace node. Automatically waits for the trace to finish if it is still running, eliminating the need for manual polling.

Instructions

Get trace node children (or root nodes if nodeId omitted). Use openl_start_trace first. While the trace is still running the backend answers 409 Conflict; by DEFAULT this tool subscribes to the studio's trace-status websocket and waits (up to waitTimeoutMs, default 120s) until the trace completes — call it once after openl_start_trace, no manual polling needed. Pass 'tableId' (the id given to openl_start_trace) when the trace was started by a different server/CLI process; otherwise the table is remembered automatically. Set wait: false for the raw immediate-409 behavior.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
waitNoWhen true (DEFAULT), if the trace is still running (backend returns 409 Conflict) the server subscribes to the studio's trace-status websocket and waits until the trace completes or waitTimeoutMs elapses — no client-side polling needed. Set false to get the raw immediate 409 behavior.
nodeIdNoParent node ID. Omit for root nodes.
tableIdNoTable id the trace was started for (the same value passed to openl_start_trace). Used to subscribe to the studio's per-table trace-status websocket topic while waiting out the 409 window. OPTIONAL when openl_start_trace ran through this same server instance — the table is remembered automatically; pass it explicitly when the trace was started by another process (e.g. a separate CLI run).
projectIdYesProject ID returned by backend. Use the exact 'projectId' value from openl_list_projects() response without modification or reformatting.
waitTimeoutMsNoMaximum time to wait for trace completion, in milliseconds. Default 120000 (2 min), cap 600000 (10 min). On timeout an error is returned explaining that the trace is still running server-side.
response_formatNoResponse format: 'json' for structured data, 'markdown' for human-readable (default), 'markdown_concise' for brief summary (1-2 paragraphs), 'markdown_detailed' for full details with contextmarkdown
showRealNumbersNoShow exact numbers instead of formatted (default: false).

Tool Definition Quality

A5/5.0
Behavior5/5

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

Discloses critical behaviors beyond annotations: the 409 Conflict response while trace is running, automatic websocket subscription to wait for completion, default and max wait time, and the effect of the 'wait' parameter. These are not covered by annotations (readOnlyHint, openWorldHint, idempotentHint).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded with the core purpose and key behavior. Every sentence adds value without redundancy. It efficiently covers usage, parameters, and edge cases.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity and the absence of an output schema, the description sufficiently explains what the tool does, when to use it, and how parameters affect behavior. It covers the waiting mechanism, error handling (409), and cross-process usage, making it self-contained for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds significant meaning beyond the input schema. For example, it explains that 'nodeId' omitted returns root nodes, 'tableId' is optional when same server instance but required for cross-process traces, and 'wait' controls immediate vs. polling behavior. This contextualizes the parameters far beyond their schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get trace node children (or root nodes if nodeId omitted)', using a specific verb and resource with scope. It distinguishes itself from sibling tools like openl_start_trace and openl_get_trace_node_details by indicating it retrieves a tree structure.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states prerequisite ('Use openl_start_trace first'), explains the default waiting behavior with timeout, and provides guidance for when to pass 'tableId' (trace started by another process). Also describes how to bypass waiting by setting 'wait: false'.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/openl-tablets/openl-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server