Skip to main content
Glama

VarynForge

by com.varynforge

Start research run

start_research_run
Destructive

Start a research run for a project — discovers keywords, evaluates competitors, and writes opportunity clusters. Consumes one credit. Returns { runId }; poll get_research_status for progress. Returns { entitlement } instead when the operator is on the free plan.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYes
contextYesOne sentence: what is the operator trying to achieve right now? Describe their goal, not this tool's purpose.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • addedInput schema / properties / context
      Added value: +{
+  "description": "One sentence: what is the operator trying to achieve right now? Describe their goal, not this tool's purpose.",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "id"
-]New value: +[
+  "id",
+  "context"
+]
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the destructiveHint annotation, the description discloses that the action consumes one credit, returns async progress via runId, and behaves differently on the free plan by returning an entitlement instead. This gives the agent a clear picture of side effects and plan-dependent behavior.

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?

Three concise sentences front-load the action and outcome, then cover credit cost, return shape, and plan variation. Every sentence adds distinct information with no repetition of the title or schema.

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?

For a simple two-parameter tool, the description covers purpose, side effects, return contract, async polling, and a plan-dependent exception. The only notable gap is the semantics of the id parameter, which is not explicitly stated as the project ID, so an agent may have to infer it from 'for a project'.

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

Parameters3/5

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

The schema documents only context with a description; id has only type/format. The tool description adds the hint that the run is 'for a project', which implies id is a project identifier, but it does not explicitly define id or explain how context should be phrased beyond the schema's own description. This is partial compensation for the 50% schema coverage.

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 uses a specific verb ('Start') and resource ('research run for a project'), and enumerates the concrete sub-actions (discovers keywords, evaluates competitors, writes opportunity clusters). It is clearly distinguishable from siblings like get_research_status by stating the run starts and returns a runId to poll.

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 clearly implies the usage context: at the beginning of a research workflow. It also routes to get_research_status for progress, though it does not explicitly state when not to use this tool or mention alternative starting-point tools. The free-plan entitlement note adds a conditional branch but is more behavioral than usage-bound.

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

All VarynForge toolsInspect
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

A3.8/5.0
Disambiguation4/5

Most tools target a distinct resource and action, and the descriptions carefully cross-reference close alternatives (e.g., add_article_suggestion vs create_article_suggestion_with_input vs accept_idea). A few brief/read variants like get_article_brief, get_write_handoff, and download_brief_markdown could still be confused despite helpful explanations, so the set is not perfectly unambiguous.

Naming Consistency5/5

Tool names follow a highly consistent verb_noun snake_case pattern throughout: get_*, list_*, create_*, update_*, set_*, add_*, delete_*, start_*, expand_*, etc. Even the less common names like lint_draft and remap_asset are still clear verb_noun constructions.

Tool Count1/5

At 57 tools, this far exceeds the 50+ extreme threshold for a single MCP server. Even for a broad content workflow, the surface is overwhelming and would benefit from consolidation or splitting into focused servers.

Completeness4/5

The tool set covers the full content lifecycle: project setup, research runs, opportunity clustering, suggestion creation, brief generation, drafting, linting, publishing, reporting, and account management. Minor gaps exist—destinations and projects cannot be deleted via MCP, and there is no direct update for article suggestion metadata—but these are workable via the web UI or existing tools.

Resources