Meta Council

Test Workflow Step

test_workflow_step

Run exactly ONE step of a workflow and return what it produced, so you can iterate on a single step's wording without running the steps before it. THIS SPENDS CREDITS EXACTLY LIKE A REAL STEP: the step runs on a real model through the same engine a full run uses and is billed identically -- it is not a simulation, a dry run, or a free preview. If you want to check a workflow's shape, parameters, models and cost estimate for free, use plan_workflow instead; that one runs nothing. Starts no session, so there is nothing to poll and nothing to advance. Requires authentication.

Input Schema

TableJSON Schema

Name	Required	Description
`query`	No	The input the step works on, exactly as you would pass it to run_workflow. Optional -- omit for a step whose instruction already carries everything it needs.
`workflow`	Yes	The workflow slug (from list_workflows), e.g. 'due_diligence'.
`parameters`	No	Optional values for the workflow's declared parameters, as a flat name-to-value object, e.g. {"region": "EU"}. They are substituted into the step wording the same way a real run substitutes them.
`step_index`	Yes	Which step to run, counting from 0. A workflow with 4 steps accepts 0 to 3; anything else is refused without spending.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes

TDQS

A4.5/5.0

Behavior4/5

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

The description clearly states it runs a real model, spends credits, is billed identically, and is not a simulation. It also notes that it starts no session and requires authentication. Annotations provide no hints, so the description carries the burden well; could add idempotency or rate limit info.

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 a single paragraph that front-loads the purpose, then provides important caveats about credits and alternatives. It is efficient but could be more scannable with bullet points for the key points.

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 (4 params, output schema exists, annotations silent), the description covers purpose, usage guidance, behavioral traits, parameter semantics, and alternatives. It provides enough for an agent to decide when and how to use it correctly.

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 100%, and the description adds significant context: it explains the query parameter's relation to run_workflow, workflows as slugs from list_workflows, parameters as flat objects with substitution, and step_index validation with cost behavior.

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 states 'Run exactly ONE step of a workflow' with a clear verb and resource, and distinguishes itself from run_workflow, advance_workflow, and plan_workflow by specifying the single-step scope and credit cost.

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?

It explicitly tells when to use (iterate on a single step's wording) and when not (for checking shape/parameters, use plan_workflow instead). It also warns about credit spending. Lacks an explicit directive against full runs, but the name and context imply it.

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

All Meta Council tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0

Disambiguation5/5

Every tool targets a distinct resource and action, with detailed descriptions that clearly separate overlapping domains (e.g., consulting vs. marketing vs. outreach). Even within the same domain, tools like 'create_consulting_deliverable' and 'create_consulting_document_revision' are unambiguous due to their specific nouns.

Naming Consistency5/5

All tools follow a consistent verb_noun snake_case pattern (e.g., 'create_invoice', 'get_deal', 'list_agents'). The few exceptions like 'locus_determine_from_scores' still adhere to the verb_noun structure and do not break the pattern.

Tool Count1/5

With 124 tools, the server is massively over-scoped for typical MCP use. The tool count far exceeds the '50+ extreme mismatch' threshold, making it nearly impossible for an agent to efficiently navigate or select the right tool without extensive context. Even a large platform should consolidate or expose fewer tools.

Completeness5/5

The tool surface covers CRUD and lifecycle operations across at least 10 domains (sales, consulting, marketing, outreach, accounting, workflows, ticketing, API keys, feedback, platform metrics). Each domain appears to have no obvious gaps—e.g., invoicing includes create, update, send, mark paid, void; ticketing includes create, update, archive, dependencies, batch, scenarios, validation.

Resources

Need Help?