Skip to main content
Glama
Sign In
dexe-mcp

dexe-mcp

by edward-arinin-web-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Flow plans and pitfalls

dexe_guide
Read-onlyIdempotent

Retrieve ordered steps, parameter questions with risk notes, and known pitfalls for multi-step DeXe tasks such as creating a DAO, launching tokens, opening sales, or passing proposals.

Instructions

Read-only, local. The plan for a multi-step or unfamiliar DeXe request — 'create a DAO', 'launch a token with distribution/OTC/staking', 'open a sale', 'pass this proposal': the ordered steps (which tools, in what order, with what params), the questions to ask the user with per-parameter risk notes, and the known pitfalls for that journey. Reference topics answer data questions the same way (flow:"read_dao_data" covers the whole read surface). No args or a free-text intent returns the menu; flow returns the full plan.

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": "dexe_guide"
  }
}

Input Schema

NameRequiredDescriptionDefault
flowNoExact flow or topic id. Takes precedence over `intent`; omit both for the menu.
intentNoThe user's request in free text — matched against the flow triggers (e.g. 'create a token and sell 20% via OTC').
chainIdNoTarget chain (56 mainnet / 97 testnet). Defaults to the last-used, then the configured default chain.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.37.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so safety needs no elaboration; the description's 'Read-only, local' is confirmatory rather than new. It does add real behavioral value by disclosing what the response contains (ordered step list, per-parameter risk notes, pitfalls) and how the argument modes resolve (no args or intent → menu, flow → full plan).

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?

Front-loaded with 'Read-only, local' and then the core purpose; the examples and the argument-mode sentence are dense but each carries useful routing information. The long em-dash-and-quote construction makes it harder to scan than a short bulleted structure would be.

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 must convey return content, and it does: plan steps, questions with risk notes, pitfalls, plus a menu mode. It is adequate for a zero-required-parameter reference tool; only the exact plan object structure is left unspecified, which matters little before invocation.

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 coverage is 100% and the schema already documents the flow enum, the intent free-text matching, and that flow takes precedence over intent. The description largely restates this dispatch logic (menu vs. full plan) rather than adding syntax, format, or edge-case detail beyond the schema.

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: it returns the ordered plan — which tools, in what order, with what params — plus user questions with risk notes and known pitfalls. Concrete example journeys ('create a DAO', 'launch a token with distribution/OTC/staking', 'pass this proposal') make clear it is a planning/reference tool, distinguishable from the action-oriented siblings like dexe_dao_create or dexe_proposal_create.

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?

Gives a clear selection condition — use it for multi-step or unfamiliar DeXe requests — and extends that to data questions via the flow:"read_dao_data" note. It stops short of an explicit exclusion (e.g. 'for a known single call, invoke that tool directly'), so the boundary for familiar, single-step operations is left implicit.

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

Deploy Server

Other Tools