mltree-mcp

Overview Schema Source Related Servers Discussions Admin

gnn_summary

Summarizes a GNN step's model architecture and datasets by statically reading scripts and imports, and reports cached graph statistics without running the code.

Instructions

GNN view of a step: the model architecture read statically from its script and imported project modules (conv layer types and counts, hidden sizes, heads, pooling, head, forward order; nothing is imported or run), dataset classes it constructs (TUDataset, MoleculeNet, QM9, OGB, DGL ...), and cached dataset stats (graphs, nodes/edges per graph, feature dims, classes or target range, self loops, isolated nodes).

Input Schema

Name	Required	Description	Default
`step`	No	One step in full (default: every step with GNN models or graph data)
`introspect`	No	Also load the step's .pt/.bin graph files to compute dataset stats. Only when the user asked for it: it runs torch.load / dgl.load_graphs in a subprocess with the project's Python, and unpickling can execute code

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.8.0Oct 24, 2026

TDQS

A4.7/5.0

Behavior5/5

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

The description excels here by contrasting two behavioral states: the default state where models are read 'statically... nothing is imported or run' versus the `introspect` state, which explicitly states that loading files 'can execute code.' This is critical behavioral context.

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

Conciseness4/5

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

The description is dense and highly technical, serving as a comprehensive single block of text. While efficient, its structure is very complex, typical of GNN tooling.

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 that an output schema exists, the description does not need to explain return values. It comprehensively defines the inputs, the scope of the summary, and the behavioral risks, making it a complete definition.

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 with 100% schema coverage, the description adds massive value, especially for the `introspect` parameter, by detailing the dangerous subprocess actions (torch.load, unpickling) that occur when that flag is set.

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 precisely defines the scope of the tool as a 'GNN view of a step,' detailing exactly what information is extracted (model architecture, dataset classes, cached stats). This highly specific definition clearly separates it from other general step management tools.

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

Usage Guidelines4/5

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

While it doesn't start with a high-level 'when to use' statement, it defines its utility by listing the specific GNN data it provides. The strong warning within the `introspect` parameter provides crucial usage guidance regarding potential execution risks.

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