Skip to main content
Glama

Workflow run

workflow_run

Execute a 1-6 step atomic multi-tool DAG workflow or curated blueprint (quant_alpha_desk, b2b_enterprise_recon, agent_due_diligence, deep_market_intel, security_surface_scan) in parallel waves with {{steps.id.path}} piping and an Ed25519 receipt. $0.015 per call over x402 or X-API-Key.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "workflow_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoOptional topic query for deep_market_intel blueprint
stepsNoOptional custom array of 1..6 DAG steps ({id, tool, params, dependsOn})
domainNoOptional target domain for recon/diligence/security blueprints
paymentNoOptional x402 payment header value
blueprintNoBlueprint: quant_alpha_desk | b2b_enterprise_recon | agent_due_diligence | deep_market_intel | security_surface_scan

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does contribute real behavior: execution happens 'in parallel waves', outputs are pipeable via {{steps.id.path}}, and an Ed25519 receipt is produced. However it omits error/failure semantics for a partially failed DAG, whether executions are idempotent or side-effecting, and any auth precondition beyond the payment modes.

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?

Two sentences, front-loaded with the action, and every clause carries weight: step limit, blueprint names, execution model, piping syntax, receipt, price, and payment methods. No filler or repetition of the tool title.

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

Completeness3/5

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

For an orchestrator with no output schema, the return shape is only hinted at ('Ed25519 receipt') — there is no indication of per-step results, ordering, or how wave failures surface. With five optional parameters and no required input, the definition also leaves the 'call with nothing' case undefined.

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%, so the baseline is 3; the description earns an extra point by explaining that steps form a DAG executed in parallel waves and that values move between steps through {{steps.id.path}} templating — meaning the schema's {id, tool, params, dependsOn} shape does not convey. The blueprint name list is largely duplicative of the schema's own enumeration.

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?

States a specific verb and resource — 'Execute a 1-6 step atomic multi-tool DAG workflow or curated blueprint' — and enumerates all five blueprints by name. That enumeration, plus the orchestration framing, distinguishes it from the single-purpose siblings (security_headers, deep_research, etc.) without needing to open a schema.

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

Usage Guidelines3/5

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

The two execution modes (custom steps vs. a named blueprint) are named, so usage is implied, but there is no guidance on when to pick a blueprint over custom steps, when to use this instead of calling the underlying sibling tools directly, or what happens if neither is supplied (all five params are optional).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources