Skip to main content
Glama
openl-tablets

OpenL MCP Server

Official

Expand Call-Tree Node

openl_expand_trace_tree
Read-onlyIdempotent

Load one level of a profiling run's call tree on demand to inspect a specific branch; expand any step with sub-calls and page large loops to find performance bottlenecks.

Instructions

Load one level of a profiling run's executed call tree on demand. The tree is lazy: the /stack tree root (a profiling openl_start_trace / openl_resume_trace with includeTree: true) and every node returned here are ONE level deep — each step carries a childrenTotal count instead of nested children. Expand a step whose childrenTotal > 0 by naming its node (uri + instance) and the step's ref; the reply is a TreeChildrenView { children, total } where each child is itself shallow (its own steps' childrenTotal), expanded by calling this tool again. Page a loop's many sub-calls with offset/limit (default 100): when total > offset + children.length the reply sets hasMore: true and nextOffset — call again with that offset to get the next page. A returned node may also carry notRetained — sub-calls that ran but were dropped once the retained tree hit its size limit (report as '+N not retained'). Requires a profiling run (profiling: true retains the tree). To find what's slow use the constant-size profile overview instead; use this to walk one branch's call structure. Valid while the debug session is alive (including after the run completes).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
uriYesSource URI of the node whose step to expand: the root node's `uri` from the /stack `tree` (a profiling openl_start_trace / openl_resume_trace with includeTree: true), or a child node's `uri` from an earlier openl_expand_trace_tree page.
stepYesReference of the step within that node to expand, e.g. 'R1C0' — a step whose `childrenTotal` > 0 (a step with childrenTotal 0 or absent made no sub-calls).
limitNoHow many sub-calls to return per page (backend default 100). Keep it modest — a page of many wide nodes can still be large.
offsetNoIndex of the first sub-call to return, for paging a loop's thousands of children (default 0). When the response's total exceeds offset + returned children, call again with offset advanced by the returned count (the reply's nextOffset).
instanceYesZero-based execution index of that node in the run (its `instance`; 0 for the root) — picks the exact loop iteration when the table ran more than once.
projectIdYesProject ID returned by backend. Use the exact 'projectId' value from openl_list_projects() response without modification or reformatting.
response_formatNoResponse format: 'json' for structured, round-trippable data (default), 'markdown' for human-readable output, 'markdown_concise' for a brief summary (1-2 paragraphs), or 'markdown_detailed' for full details with contextjson
Behavior5/5

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

The annotations already declare readOnly, idempotent, and openWorld hints, so the safety profile is covered. The description adds substantial behavioral detail beyond those hints: the lazy one-level expansion model, `childrenTotal` instead of nested children, paging via `hasMore`/`nextOffset`, `notRetained` dropped sub-calls, the profiling prerequisite, and validity after the run completes. No statement contradicts the annotations.

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 long but every sentence earns its place: it covers purpose, prerequisites, pagination, special cases like `notRetained`, and the alternative tool. It is front-loaded with the core action, then unfolds the lazy-tree model and paging details in a logical order. Given the tool's complexity and the absence of an output schema, the density is appropriate rather than bloated.

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?

With no output schema present, the description carries the full burden of explaining the return shape, and it does: the reply is a TreeChildrenView { children, total }, with `hasMore` and `nextOffset` for paging, and possible `notRetained` counts. It also covers lifecycle constraints (profiling run required, valid while the debug session is alive) and how to start from the /stack `tree` root. Nothing needed for correct invocation is missing.

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?

Even though schema coverage is 100%, the description adds meaning the schema alone does not fully convey. It explains that `step` must reference a node with `childrenTotal > 0`, that `offset`/`limit` page a loop's many sub-calls with `nextOffset`, and that `instance` picks the exact loop iteration. This transforms the parameters from raw JSON fields into a coherent iteration contract.

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 opens with a specific verb and resource: 'Load one level of a profiling run's executed call tree on demand.' It also distinguishes itself from sibling tools by naming the lazy-tree mechanism, the /stack `tree` root, and the alternative 'constant-size `profile` overview' for finding slow spots. This makes it unmistakable which operation this tool performs and how it differs from nearby tracing tools.

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?

The description explicitly states when to use this tool: only for a profiling run with `includeTree: true`, and only for expanding nodes whose `childrenTotal` is greater than 0. It also gives a clear when-not-to-use directive: 'To find what's slow use the constant-size `profile` overview instead; use this to walk one branch's call structure.' This is explicit routing with no ambiguity.

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