Skip to main content
Glama
brilliantdirectories

brilliant-directories-mcp

Official

createSubCategory

Create a sub-level member category under an existing top category. Requires parent category ID and name, supports optional URL slug and sub-sub nesting.

Instructions

Create a service - Create a new SUB-level member category under an existing Top Category. Writes live data.

A Sub Category is level 2 of the 3-tier member classification. It MUST have a parent Top Category (via profession_id). It may optionally sit under another Sub Category (for sub-sub-category nesting, via master_id). Backed by BD's list_services table.

Use when: explicitly adding a sub-category BEFORE assigning members to it. If creating/updating a user who needs a sub-category that doesn't exist yet, on createUser just include the name in services - BD auto-creates it. On updateUser, pass create_new_categories=1 to allow inline creation. For sub-sub nesting pass master_id=<parent service_id>; otherwise set master_id=0 for direct-under-Top.

Required: name, profession_id.

Pre-check before create: BD does NOT enforce uniqueness on filename (URL slug) or name - but uniqueness IS scoped per-parent (two sub-cats with the same filename under different profession_id is fine; same filename under the SAME profession_id is not). Do a server-side filter-find: listSubCategories property=filename property_value=<proposed> property_operator==, then filter results by the intended profession_id. Zero rows under that parent = slug free; >=1 row = taken (URL collision - wrong sub-cat page resolves). Do NOT paginate unfiltered lists - filtered lookup is one tiny response. If taken: reuse via updateSubCategory, OR ask the user, OR pick an alternate filename and re-check. Wrapper safety net: on a missed pre-check, the wrapper auto-suffixes filename on collision (-1...-20) and surfaces the suffix in the response. Pre-checking still preferred — auto-suffix surprises the caller in URL-sensitive workflows.

Parameter guidance:

  • name - human-readable (e.g. "Sushi")

  • profession_id - the parent Top Category's ID (from listTopCategories or createTopCategory)

  • master_id - for SUB-SUB-CATEGORY nesting, pass the parent Sub Category's ID; default 0 means "directly under the Top Category"

  • filename - URL-slug form; desc, keywords, sort_order, lead_price, image - all optional

See also: updateSubCategory (modify), listSubCategories (list), createTopCategory (create parent).

Writes live data: changes are immediately visible on the public site.

Returns: { status: "success", message: {...createdRecord} } including service_id. Use that to assign members via updateUser.services (CSV) or createMemberSubCategoryLink.

How a member gets classified on their public profile:

  • users_data.profession_id -> points at a single Top Category (the member's primary classification; shown in URL slug)

  • users_data.services -> CSV of Sub Category IDs the member is tagged with (multiple allowed; simpler than the join table)

  • rel_services rows (Member ↔ Sub Category links) -> used when you need per-link metadata like avg_price, specialty, num_completed. Optional; most sites use just the CSV field.

Sub-sub-categories: createSubCategory with master_id=<parent service_id> creates a Sub Category nested under another Sub Category (a "sub-sub"). master_id=0 (default) means the Sub Category sits directly under a Top Category (the profession_id).

There is NO createProfession or createService tool in this MCP — those are BD's internal table names. Use createTopCategory / createSubCategory instead (BD's table-name → tool-name mapping is documented in Rule: Table to endpoint).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
profession_idYesParent category ID
descNoShort internal taxonomy-row label. **Even if the user says "description" - this is NOT an SEO description.** Not a meta-tag surface, not Google-ranking copy, not the H1/intro on the public category search page. Most BD themes don't render this field. For ANY SEO task on a category or sub-category - "write a description that ranks," "improve SEO," "add meta tags," "write intro copy" - create a WebPage with `seo_type=profile_search_results` and the matching slug instead (see `createWebPage`). Short internal blurb only here.
filenameNoURL slug. Must be unique across web pages, top categories, sub categories, plan public URLs, and member profile slugs (wrapper auto-rejects collisions; pick a different slug or rename the conflict first).
keywordsNoFuzzy-search synonyms for on-site category matching - NOT SEO meta-keywords. Comma-separated single words (no spaces): synonyms, abbreviations, slang, common misspellings. Example for `Doctor`: `doc,physician,md,medic,gp,specialist`. ~5-10 max. Skip SEO phrases like `doctor near me` - those aren't fuzzy matchers. Optional.
sort_orderNo
lead_priceNo
master_idNo
Behavior4/5

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

Annotations indicate readOnlyHint=false, confirming mutation. The description goes beyond by stating 'Writes live data' and 'changes are immediately visible on the public site.' It also explains the auto-suffix safety net for filename collisions and the return format, adding behavioral context not captured in annotations.

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?

The description is long but well-structured with clear sections (purpose, usage, pre-check, parameter guidance, see also, returns, classification). Every sentence adds value given the tool's complexity and the need to differentiate from alternatives. Some extra context on member classification could be moved to a separate reference but is still relevant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (8 parameters, no output schema, openWorldHint=true), the description is remarkably complete. It covers usage scenarios, pre-check steps, parameter details, uniqueness constraints, return format, and even explains how member classification works in the broader system. No gaps are apparent.

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

Parameters4/5

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

Schema description coverage is 50% (only 4 of 8 parameters have descriptions). The description compensates by explaining each parameter in plain language (e.g., name, profession_id, master_id, filename). It adds usage context beyond the schema, such as the meaning of master_id for sub-sub-categories and the need for profession_id to link to a Top Category.

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 clearly states the tool's purpose: 'Create a service - Create a new SUB-level member category under an existing Top Category.' It distinguishes itself from sibling tools like createTopCategory (which creates parent categories) and provides context on hierarchy levels.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

The description explicitly states when to use this tool ('explicitly adding a sub-category BEFORE assigning members to it') and when not to (use createUser or updateUser with auto-creation). It names alternatives like createUser, updateUser, and updateSubCategory. It also gives pre-check instructions for filename uniqueness.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/brilliantdirectories/brilliant-directories-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server