Skip to main content
Glama
Sign In

TradeGraph

by ai.rinda.tradegraph
OverviewDiscussionsAdmin

Step-by-step export workflows (certification, FTA origin, documents, payment, buyer checks …)

export_workflow
Read-onlyIdempotent

36 step-by-step expert workflows for the export jobs around the data — what exporters usually learn too late: export readiness check (blind spots, 90-day plan), certification and registration in each market (FDA, MoCRA, CPNP, NMPA, halal, CE, PSE …) and in whose name, labels, HS code, regulation watch, export control and sanctions screening, FTA origin and certificates of origin, export documents (PI, CI, packing list, L/C), logistics, Incoterms, samples and dangerous goods, pricing and quotes, payment terms, L/C and export credit insurance, duty drawback and zero-rated VAT, Korean export support programs (vouchers, certification and trade-show subsidies) and grant applications, buyer due diligence and fraud checks (changed bank details), trademarks, distribution agreements, claims and unpaid invoices, trade shows, buyer outreach, reply triage, sales kits, influencer seeding, marketplaces, cross-border e-commerce and creative. Call with job (what the user asked, in their words and language) to get the best-matching workflow in full plus the next matches; with name for a known one; with neither to list them all by stage. Follow the steps in order: each names the TradeGraph tools to call (gtm_plan, blind_spots, price_ladder …) and the official sources to check. The same text as TradeGraph's Agent Skills and Claude Code plugin. Free, read-only.

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": "export_workflow"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobNoWhat the user wants done, in their own words and any language (e.g. '이 바이어 믿어도 돼? 입금 계좌가 바뀌었대', 'the US buyer wants an FTA certificate of origin', 'first export, what are we missing?'). Returns the best-matching workflow.
fileNoOptional, with name: a reference file the workflow mentions, e.g. 'references/sources.md'.
nameNoA workflow name (from the list, or a name a TradeGraph answer mentions such as certification-check).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already carry readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds value beyond that: it discloses the return shape ('the best-matching workflow in full plus the next matches', or a listing by stage) despite there being no output schema, and notes parity with Agent Skills / the Claude Code plugin plus 'Free, read-only'. It does not mention any ranking/ambiguity limits on the job matching.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence is a ~150-word comma-separated dump of every topic covered, which largely duplicates the enum of workflow names in the schema. The actionable instructions ('Call with job...', 'Follow the steps in order') are pushed to the end instead of being front-loaded. A shorter description could carry the same operational value.

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?

With no output schema, the description does its job by explaining what comes back (a full workflow with next matches, or a full list by stage) and how the returned steps relate to other TradeGraph tools. Combined with 100% schema coverage of the three parameters, an agent has enough to call it correctly; only the matching/ranking behavior on ambiguous job strings is unstated.

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?

Schema description coverage is 100%, so job, name and file are already fully documented, including examples and the enum of workflow names. The description restates the job/name/neither routing but adds no syntax, matching behavior, or fallback guidance beyond the schema. Baseline 3 applies since the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description makes clear this is a workflow-retrieval tool over 36 export playbooks, and the sentence 'Call with job ... to get the best-matching workflow in full plus the next matches' states the operation concretely. It also distinguishes itself from siblings by explaining that each workflow names the TradeGraph tools to call (gtm_plan, blind_spots, price_ladder), so the agent knows this is an entry point rather than a direct executor. The purpose is nonetheless buried behind a long topical enumeration.

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 gives explicit routing for all three parameter modes: job for a natural-language request, name for a known workflow, neither to list everything by stage. It also instructs 'Follow the steps in order' once a workflow is returned. What is missing is an explicit statement of when not to use it (e.g. when you already know the concrete tool to call), but the implied usage is unambiguous.

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

All TradeGraph toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources