Skip to main content
Glama
Coalesce-Software-Inc

coalesce-transform-mcp

Official

Create Pipeline from SQL

create_pipeline_from_sql

Plan and create a Coalesce pipeline from exact user SQL, automatically resolving workspace sources and generating compatible nodes.

Instructions

Plan and create a Coalesce pipeline from user-provided SQL. Pass the user's EXACT SQL unchanged. The SQL may use raw table names or already contain Coalesce {{ ref() }} syntax if that is what the user provided. Do NOT rewrite between styles or otherwise modify the query. The planner resolves workspace sources automatically and generates a Coalesce-compatible joinCondition for the final node.

If you are building a pipeline yourself, use declarative tools directly: create_workspace_node_from_predecessor → convert_join_to_aggregation → replace_workspace_node_columns.

This tool validates candidate node types against currently observed workspace nodes. If a selected type is not observed, the plan will include a warning asking the user to confirm installation in Coalesce.

Consult coalesce://context/node-type-corpus for node type patterns and metadata structures.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sqlYesThe user's EXACT SQL, copied verbatim. It may use raw table names or existing Coalesce {{ ref() }} syntax. Do NOT rewrite between SQL styles or modify it in any way. Pass it exactly as the user provided it.
goalNoOptional business goal or context for the SQL
dryRunNoWhen true, return the generated plan without creating nodes.
schemaNoOptional target schema
databaseNoOptional target database
repoPathNoOptional local committed Coalesce repo path for repo-first node-type ranking. Falls back to COALESCE_REPO_PATH or `repoPath` in the active ~/.coa/config profile when omitted.
confirmedNoSet to true only after presenting the ready plan to the user and receiving explicit approval. Must be paired with the confirmationToken returned by the prior STOP_AND_CONFIRM response.
targetNameNoOptional target node name override
descriptionNoOptional node description
workspaceIDYesThe workspace ID
locationNameNoOptional target locationName
targetNodeTypeNoOptional node type override. When omitted, the planner ranks repo-backed and observed workspace node types for the use case.
configOverridesNoOptional config overrides to merge into the final node body.
confirmationTokenNoThe token returned in the STOP_AND_CONFIRM response. Required when confirmed=true to prove the plan was presented to the user.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
planNo
errorNo
dryRunNo
reasonNo
createdNo
warningNo
cancelledNo
nodeCountNo
incompleteNo
workspaceIDNo
createdNodesNo
cleanupFailuresNo
STOP_AND_CONFIRMNo
failedPlanNodeIDNo
cleanupFailedNodeIDsNo
Behavior5/5

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

The description goes beyond annotations by disclosing that SQL is passed unchanged, planner auto-resolves sources, validates node types, warns if type not observed, and requires confirmation token. No contradiction with annotations.

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 structured in clear paragraphs: core purpose, alternative usage, validation behavior, consultation reference. It is informative without being overly verbose, though could be slightly more concise.

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 (14 params, nested object, output schema exists), the description covers essential behavior, usage boundaries, and parameter semantics. It is complete and provides sufficient context for an AI agent to use the tool correctly.

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?

Schema coverage is 100% with good descriptions. The description adds significant usage context for parameters like sql (must be exact), confirmed/confirmationToken pairing, and dryRun purpose. Baseline 3, but value add justifies 4.

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 the tool plans and creates a pipeline from user-provided SQL. It specifies the exact verb and resource, and distinguishes from sibling tools by explicitly noting an alternative tool sequence for manual pipeline building.

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 provides explicit usage guidance: use when user provides SQL, not when building manually (alternative tools given). It also mentions validation behavior and consultation of node-type corpus.

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/Coalesce-Software-Inc/coalesce-transform-mcp'

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