Skip to main content
Glama
Coalesce-Software-Inc

coalesce-transform-mcp

Official
by Coalesce-Software-Inc
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

Start Run

start_run

Initiates a new Coalesce refresh run using Snowflake credentials. Specify environment, workspace, job, node selectors, or confirm run of all nodes to start execution.

Instructions

Start a new Coalesce refresh run. Returns a task that resolves once the run has been submitted.

Requires Snowflake auth — credentials read from environment variables (Key Pair: SNOWFLAKE_KEY_PAIR_KEY, or PAT: SNOWFLAKE_PAT, plus SNOWFLAKE_USERNAME, SNOWFLAKE_WAREHOUSE, SNOWFLAKE_ROLE).

Provide exactly one of runDetails.environmentID or runDetails.workspaceID. If the user provides a job name, look up the ID with find_jobs_by_name (or list_environment_jobs) first.

Args:

  • runDetails.environmentID (string, optional): Target deployed environment (numeric ID as string)

  • runDetails.workspaceID (string, optional): Target workspace for a development run (numeric ID as string)

  • runDetails.jobID (string, optional): Specific job to run

  • runDetails.includeNodesSelector (string, optional): Node filter for ad-hoc runs

  • runDetails.excludeNodesSelector (string, optional): Node exclusion filter

  • runDetails.parallelism (number, optional): Max parallel nodes (default: 16)

  • runDetails.forceIgnoreWorkspaceStatus (boolean, optional): Allow run even if last deploy failed

  • confirmRunAllNodes (boolean): Required when no job/node scope is provided

  • parameters (object, optional): Key-value runtime parameters

Returns: { runCounter: number, runStatus: string, message: string }

Prefer run_and_wait when you need the final outcome in a single call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
parametersNoArbitrary key-value parameters to pass to the run
runDetailsYes
confirmRunAllNodesNoMust be set to true when no jobID, includeNodesSelector, or excludeNodesSelector is provided. This confirms you intend to run ALL nodes in the target.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
messageNo
runStatusNo
runCounterNo

Tool Definition Quality

A4.7/5.0
Behavior4/5

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

Annotations already indicate non-read-only and non-destructive. Description adds value by explaining auth setup, that it returns a task for submission, and that it requires Snowflake credentials. Could be improved by noting possible async behavior or failure modes, but overall good.

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?

Well-structured: one-sentence purpose, followed by auth, parameter guidance, args list with types, returns format, and alternative tool. No wasted words, every sentence serves a purpose.

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

Completeness4/5

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

Given complexity (nested objects, auth dependencies, multiple run types), the description covers key aspects: submission mechanism, parameter constraints, and return value. Mentions output schema indirectly via 'Returns: {...}'. Could mention polling status or concurrency limits, but run_and_wait covers final outcome.

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?

Schema coverage is 67%, but description significantly augments with usage rules: 'Provide exactly one of environmentID or workspaceID', 'If the user provides a job name, look up the ID...', default parallelism, and note on confirmRunAllNodes. Adds clear meaning beyond 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?

Clearly states 'Start a new Coalesce refresh run' with specific verb and resource. Distinguishes from sibling tools like run_and_wait by mentioning it returns a task for submission, not the final outcome.

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?

Provides explicit when-to-use guidance: prefers run_and_wait for final outcome. Details required auth (Snowflake env vars), mutual exclusivity of environmentID/workspaceID, and mentions looking up job IDs with other tools. Covers confirmRunAllNodes requirement.

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