Skip to main content
Glama
shopino-mcp

shopino-mcp

by sepehr071

List categories

sh_categories
Read-onlyIdempotent

List the category tree with IDs, URL paths, levels, and product and shop counts. Search all levels by Persian name or English slug to find a category ID, or browse up to a chosen depth.

Instructions

List the category tree with ids, URL paths and levels, plus total product and shop counts.

Use to get a category_id. A query searches every level; without one only levels up to max_level are listed.

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": "sh_categories"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoPersian name or English slug path, e.g. 'مانتو' or 'sneakers'.
max_levelNoDeepest level without a query.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.5.0
    • changedInput schema / properties / max_level / description
      Previous value: -"Deepest level without a query (1 = the 14 top categories)."New value: +"Deepest level without a query."
    • removedInput schema / properties / query / anyOf
      Removed value: -[
      -  {
      -    "minLength": 2,
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • changedInput schema / properties / query / description
      Previous value: -"Filter on Persian name or English slug path, any level, e.g. 'مانتو' or 'sneakers'."New value: +"Persian name or English slug path, e.g. 'مانتو' or 'sneakers'."
    • addedInput schema / properties / query / minLength
      Added value: +2
    • addedInput schema / properties / query / type
      Added value: +[
      +  "string",
      +  "null"
      +]
  2. Changed6 schema fields changedv0.3.0
    • changedInput schema / properties / max_level / description
      Previous value: -"Deepest level to list when no query is given (1 = the 14 top categories)."New value: +"Deepest level without a query (1 = the 14 top categories)."
    • removedInput schema / properties / max_level / title
      Removed value: -"Max Level"
    • changedInput schema / properties / query / description
      Previous value: -"Optional filter on the Persian name or English slug path, any level, e.g. 'مانتو' or 'sneakers'."New value: +"Filter on Persian name or English slug path, any level, e.g. 'مانتو' or 'sneakers'."
    • removedInput schema / properties / query / title
      Removed value: -"Query"
    • removedInput schema / title
      Removed value: -"sh_categoriesArguments"
    • changedOutput schema / (root)
      Previous value: -{
      -  "additionalProperties": true,
      -  "title": "sh_categoriesDictOutput",
      -  "type": "object"
      -}New value: +null
  3. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare this a read-only, idempotent, non-destructive open-world lookup, so the safety profile is covered. The description adds genuinely new behavior: a query searches every level, while without one the result is silently truncated at max_level — an important default that would otherwise surprise an agent.

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 tight sentences with the resource and return payload front-loaded, then the usage and mode behavior. No filler, though the phrase "A query searches every level" is a little terse and slightly separated from the parameter it describes.

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-optional-parameter read tool with full annotation coverage, the description covers what it returns, why to call it, and how the parameters interact. The only omission is scale behavior — no note on tree size, nesting depth limits, or whether counts are exact — but there is no output schema requiring further explanation.

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%, so both parameters (with examples and min/max bounds) are already documented, making 3 the baseline. The description does add one real semantic point — that the query overrides the level restriction — but it does not clarify the query format relationship (Persian name vs. English slug path) beyond what the schema example already shows.

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?

States a specific verb and resource (list the category tree) and enumerates the returned fields: ids, URL paths, levels, product and shop counts. The purpose is unambiguous, but it never names or distinguishes itself from siblings such as sh_search or sh_filters, which also surface categories.

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?

"Use to get a category_id" gives a concrete triggering condition, and the sentence about query vs. no-query explains the two operating modes. It stops short of naming an alternative tool or stating when not to use this one (e.g. when you already have a category_id).

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