Skip to main content
Glama
milligold-mcp

milligold-mcp

by sepehr071

Milli.gold latest posts

mg_latest_posts
Read-onlyIdempotent

List recent news, magazine, or help posts from Milli.gold with dates, categories, summaries, and URLs, filtered by section and result limit.

Instructions

List the newest posts on Milli.gold's news, magazine or help site, with date, categories, summary and URL.

Persian text. Only the newest posts exist (about 20 news, 10 mag, 10 help). Read one with mg_read.

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": "mg_latest_posts"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNewest first.
sectionNonews = daily price and market news, mag = buying guides, help = how-to articles.news

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.3.0
    • changedInput schema / properties / limit / description
      Previous value: -"How many posts to return, newest first (1-20)."New value: +"Newest first."
    • changedInput schema / properties / section / description
      Previous value: -"news = daily gold price and market news, mag = gold buying guides, help = how to use Milli."New value: +"news = daily price and market news, mag = buying guides, help = how-to articles."
  2. Addedv0.2.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds genuinely useful non-annotated context: results are Persian-language, the corpus is fixed and small (about 20 news, 10 mag, 10 help), and only recent items are retrievable, which tells an agent not to attempt deep historical queries.

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?

Two short blocks, front-loaded with purpose and fields, then constraints. The 'Persian text.' fragment is telegraphic but informative and costs almost nothing; no sentence is padding.

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 two-parameter, fully documented list tool with no output schema, the description supplies the return fields, language, and corpus ceiling that the schema cannot. It stops short of noting whether a title field is returned (only summary is mentioned) or that ordering is guaranteed strictly newest-first across sections.

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% and the enum values are already explained in the schema (news = daily price/market news, mag = buying guides, help = how-to articles). The description only paraphrases the section names as 'news, magazine or help site' and adds nothing about limit behavior beyond ordering, so baseline 3 applies.

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 ('List the newest posts') scoped to three named sections of Milli.gold, and enumerates the returned fields (date, categories, summary, URL). It also contrasts itself with mg_read ('Read one with mg_read'), so an agent can distinguish listing from reading without opening 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 Guidelines4/5

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

Gives a clear when-to-use ('list newest posts') and an explicit alternative for the follow-up step ('Read one with mg_read'), plus a hard boundary that only ~40 posts exist total. It does not address the potential overlap with mg_help_topics, which is the one sibling whose scope could be confused with the help section.

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