Skip to main content
Glama
beel-es

BeeL MCP server

Official
by beel-es
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

beel_list_customers

Read-onlyIdempotent

Retrieve a paginated list of a company's customers with optional filters by name, NIF, email, phone, city, province, and active status to find or page through customer records.

Instructions

Returns a paginated list of the customers of this company, with optional filters. Only the customers of the company in the path are returned.

Endpoint: GET /v1/companies/{company_id}/customers

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nifNoFilter by NIF (partial search)
cityNoFilter by city
pageNoPage number, starting at 1. The response echoes it back as `pagination.current_page`.
emailNoFilter by email (partial search)
limitNoHow many items to return per page. The response echoes it back as `pagination.items_per_page`.
phoneNoFilter by phone (partial search)
activeNoFilter by active/inactive status. Defaults to `true`, so inactive customers must be requested explicitly with `active=false`. Deleted customers are never returned by either value.
searchNoGlobal search by name, NIF or email
sort_byNoField to sort by. Results are always tie-broken by a stable internal key, so paging through the collection never repeats or skips a customer.legal_name
provinceNoFilter by province
company_idYesUnique identifier (UUID) of the company the operation acts on — its identifier, not its NIF. It is the only source of context: the account that owns it is derived from it, and the `BeeL-Active-Company` header plays no part. A company you do not reach answers `403`, and so does a company that does not exist, so the existence of a company in another account is never disclosed.
legal_nameNoFilter by legal name (partial search case-insensitive)
sort_orderNoSort order directionasc

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.9.0
    • changedInput schema / $defs / CustomerSortBy / description
      Previous value: -"Customer field the list is ordered by."New value: +"Customer field the list is ordered by. Ties are broken by customer id, so pages are\nstable.\n\n- `legal_name`: legal name.\n- `nif`: tax identifier.\n- `email`: email address.\n- `phone`: phone number.\n- `city`: city of the address.\n- `province`: province of the address.\n- `active`: whether the customer is active.\n- `created_at`: creation instant.\n"
  2. Changed4 schema fields changedv0.5.0
    • removedInput schema / $defs / CustomerSortBy / example
      Removed value: -"legal_name"
    • removedInput schema / $defs / SortOrder / example
      Removed value: -"desc"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / company_id / description
      Previous value: -"NIF (company) the operation acts on. It is the only source of context: the account that owns it is derived from it, and the `BeeL-Active-Company` header plays no part. A NIF you do not reach answers `403`, and so does a NIF that does not exist, so the existence of a NIF in another account is never disclosed."New value: +"Unique identifier (UUID) of the company the operation acts on — its identifier, not its NIF. It is the only source of context: the account that owns it is derived from it, and the `BeeL-Active-Company` header plays no part. A company you do not reach answers `403`, and so does a company that does not exist, so the existence of a company in another account is never disclosed."
  3. First observedv0.3.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds useful scope context (company-path-bound results) but says nothing about pagination semantics, default active filtering, or that deleted customers are excluded — that detail only lives in the schema.

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?

Three short sentences, front-loaded with purpose then scope, with no filler. The trailing 'Endpoint:' line is mildly redundant with the company_id description but remains cheap and informative.

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 straightforward read-only list tool with annotation coverage and 100% schema documentation, the description is adequate: it names the resource, the scope and pagination nature. No output schema exists, but pagination shape is echoed back via the documented page/limit descriptions, leaving only minor gaps around return payload details.

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% across all 13 parameters, so the baseline is 3. The description only gestures at 'optional filters' and adds no meaning beyond what the schema already documents for each filter, sort and pagination field.

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+resource ('Returns a paginated list of the customers of this company') and adds the scoping rule that only customers of the company in the path are returned. Clear enough to distinguish from the single-customer sibling beel_get_customer, but no sibling is named explicitly.

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

Usage Guidelines3/5

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

Usage is implied: 'with optional filters' and 'Only the customers of the company in the path are returned' tell the agent this is a scoped, filterable collection read. There is no explicit when-to-use guidance versus beel_list_stats or other listing siblings, and no exclusions.

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