Skip to main content
Glama

Rebuild network from a spec

rebuild_network
Destructive

Reconstruct a network inside a COMP from a JSON spec, creating nodes, applying parameters, and wiring inputs. Returns created nodes, wire count, and any warnings.

Instructions

Reconstruct a live network inside a COMP from a serialize_network spec — the REBUILD half of a git-diffable round-trip. Takes a JSON spec of nodes (name, operator type, parameters as constants/expressions/binds, inbound wires by name, optional x/y) and, in one pass, creates every node, applies its parameters and expressions, then wires inputs by resolving each from reference to the freshly created node. Fail-forward: an unknown operator type, missing parameter, or unresolved wire becomes a warning and the rest still build, so a partial reconstruction still returns useful results. Set clear_existing to delete the parent's current children first (destructive). Returns the created node names, wire count, parameters set, and any warnings.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
parent_pathYesCOMP to rebuild the network inside.
specYesA serialize_network spec to reconstruct.
clear_existingNoDelete existing children of parent_path first (destructive).
Behavior5/5

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

The description fully discloses behavioral traits beyond annotations: one-pass creation, parameter application, wiring, and fail-forward error handling. It explicitly notes that clear_existing is destructive. No contradictions with annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=true) exist.

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 concise (7 sentences) and well-structured, front-loading the purpose, then detailing behavior, parameters, and return values. Every sentence provides value without redundancy.

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 tool's complexity (3 parameters, nested objects, no formal output schema), the description is remarkably complete. It covers the spec structure, fail-forward behavior, destructive flag, and return fields (node names, wire count, parameters, warnings), leaving no significant gaps.

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

Parameters4/5

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

Although schema description coverage is 100%, the description adds essential context: it explains the overall process of node creation, parameterization, and wiring, and clarifies how parameters (constants, expressions, binds) are applied. This moves beyond the schema's individual property 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 defines the tool as reconstructing a live network from a serialize_network spec, explicitly positioning it as the counterpart to serialize_network in a round-trip. The verb 'reconstruct' and resource 'live network inside a COMP' are specific, and the context differentiates it from siblings like serialize_network, repair_network, and create_* 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?

The description provides clear usage guidance through the fail-forward behavior, indicating the tool is suitable for partial or error-prone specs. It also explains the destructive nature of clear_existing. However, it does not explicitly state when to avoid this tool or mention alternatives, preventing a top score.

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/Pantani/tdmcp'

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