Archicad-MCP

Overview Schema Source Related Servers Discussions Admin

Delete elements

delete_elements

Destructive

Deletes Archicad elements by GUID, requiring confirmation for irreversible removal. Returns deleted counts and reasons for any refusals in the active window.

Instructions

Delete elements. IRREVERSIBLE. Refuses without confirm=true. Archicad deletes only elements in the database of the active window and still answers success for the rest (a floor-plan label cannot be deleted while a Layout is active), so elements it would refuse (another view's, on a hidden layer, not reserved in Teamwork, locked, in a hotlinked module, or not found) are not sent, and the rest are read back afterwards. Returns requested; deleted, the count that is really gone; not_deleted grouped by reason with the GUIDs; active_window when anything was refused up front; and stopped if the delete command itself errored.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`port`	No
`guids`	Yes
`confirm`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Aug 20, 2026

TDQS

A4/5.0

Behavior5/5

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

Goes far beyond the destructiveHint=true / readOnlyHint=false annotations: it declares IRREVERSIBILITY, the confirm gate, the active-window-only deletion semantics, the fact that refused elements are silently excluded, the read-back verification, and the exact reasons an element may be skipped (other view, hidden layer, Teamwork reservation, locked, hotlink). This is unusually rich behavioral disclosure for a destructive tool.

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 the essential facts ('Delete elements. IRREVERSIBLE. Refuses without confirm=true.') and contains no filler. The final run-on sentence enumerating return fields is dense and partially redundant with the existing output schema, which slightly dilutes its efficiency.

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?

For a destructive, irreversible tool with an output schema, the description supplies everything an agent needs: the safety gate, scope limitations, silent-skip behavior, and verification. Nothing material is missing.

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 0% for 3 parameters, so the description must compensate. It explains the semantics of confirm well (must be true or the call is refused) and implies guids are the elements targeted, but the port parameter is never mentioned and guids get no format/scope detail.

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 ('Delete elements') that an agent can immediately distinguish from mutating siblings like release_elements or reserve_elements. It does not, however, explicitly call out which sibling to prefer in ambiguous cases, so it stops short of a 5.

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?

Gives one concrete precondition ('Refuses without confirm=true'), which is genuine usage guidance, but never states when to choose this over alternatives such as release_elements or set_element_data, nor any exclusion beyond the confirm gate.

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