Skip to main content
Glama
Sign In
nubiia-dev

MCP Holded

by nubiia-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

get_taxes

Retrieve all available sales and purchase taxes from Holded, optionally selecting specific fields or returning only the item count for compact tax lookups.

Instructions

Get all available taxes (Holded API v2). The v2 /taxes endpoint returns the complete tax list in one response (no cursor, no pagination). Supports fields to select specific fields and summary to return only the item count. Amounts are strings with decimal comma. Each tax has: key (the stable identifier, e.g. "s_iva_21"/"p_iva_21" — this is the value used in a document line's taxes[]), id (mirrors key), name, amount (the percentage as a string, e.g. "21"), scope ("sales" or "purchase"), group (e.g. "iva"), and type.

Input Schema

NameRequiredDescriptionDefault
fieldsNoSelect specific fields to return (e.g., ["key", "name", "amount", "scope"]). Reduces response size. If not provided, returns default fields: id, key, name, amount, scope, group, type. NOTE: the tax rate field is `amount` (not `percentage`) and the identifier is `key`.
summaryNoReturn only the item count without the full list (default: false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.0.3
    • removedInput schema / properties / page
      Removed value: -{
-  "description": "Page number (starting from 1, default: 1)",
-  "type": "number"
-}
    • removedInput schema / properties / pageSize
      Removed value: -{
-  "description": "Number of items per page (default: 50, max: 500)",
-  "type": "number"
-}
    • changedInput schema / properties / summary / description
      Previous value: -"Return only total count and page count without items (default: false)"New value: +"Return only the item count without the full list (default: false)"
  2. Changed1 schema field changedv1.7.0
    • changedInput schema / properties / fields / description
      Previous value: -"Select specific fields to return (e.g., [\"id\", \"name\", \"percentage\"]). Reduces response size by 70-90%. If not provided, returns default fields: id, name, percentage"New value: +"Select specific fields to return (e.g., [\"key\", \"name\", \"amount\", \"scope\"]). Reduces response size. If not provided, returns default fields: id, key, name, amount, scope, group, type. NOTE: the tax rate field is `amount` (not `percentage`) and the identifier is `key`."
  3. First observedv1.6.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does substantial work: it discloses no pagination, single-response behavior, string-typed amounts with decimal comma (a real parsing trap), default field set, and the key-vs-id relationship. It stops short of stating auth requirements or that the operation is read-only, but the 'Get' framing makes the latter obvious.

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 purpose and pagination behavior, then the field inventory. Every clause carries information, though the long single-paragraph field enumeration would read better as a list; nothing is redundant.

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?

No output schema and no annotations, so the description must (and does) describe the return shape in full, including field meanings and value formats. Only auth/permission context is absent, which is a modest gap for a read endpoint with zero parameters required.

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 coverage is already 100%, so the baseline is 3; the description adds genuine meaning on top by warning that the rate field is `amount` not `percentage` and the identifier is `key`, and by naming the default field set returned when `fields` is omitted.

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 ('Get all available taxes') plus the API version, and immediately clarifies scope: the complete tax list in one response with no cursor or pagination. An agent knows exactly what it gets without opening the 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?

No competing tax sibling exists, so alternative routing isn't needed, and the description instead supplies the key usage hook: `key` is the value to place in a document line's `taxes[]`. It also tells when to use `fields` (reduce size) and `summary` (count only), but doesn't give an explicit 'use this before creating a document' framing.

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