Skip to main content
Glama
Constructor Research MCP

Constructor Research MCP

by NRGGIT

delete_path

Destructive

Delete files or folders, including all folder contents, from a project disk. Preview deletion first with confirm_required, then repeat with confirm=true; this cannot be undone.

Instructions

Delete files/folders (folders with all contents) on a project disk. Send every path for the request in one call: without confirm it returns what would be deleted (confirm_required) for the user to approve once; repeat with confirm=true. Cannot be undone.

Input Schema

NameRequiredDescriptionDefault
pathsYesAll files/folders to delete for this request, approved together. Folders are deleted with all contents.
confirmNofalse (default) returns the full list for the user to approve once; true performs it.
desk_idNo
desk_urlNoLink to the Constructor desk the user copied from the browser, e.g. https://constructor.app/research/projects/<project>/desks/<desk>/viewer/file. Supplies project_id and desk_id; ask the user for it instead of choosing a project or desk yourself.
project_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds the crucial preview/confirm_required workflow and 'Cannot be undone', which the annotations do not convey. No coverage of permissions, auth, or partial-failure behavior for some of up to 100 paths.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and destruction scope, followed by the required call protocol and the irreversibility warning. No filler.

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 exists, yet the description explains the confirmation return shape, which is the main thing an agent needs. Missing only edge-case handling (partial failure across 100 paths, behavior when paths don't exist).

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 60%; the description meaningfully adds the batching semantics for paths ('Send every path for the request in one call') and the confirm contract. desk_id and project_id remain undocumented in the description, though desk_url's schema entry covers how to obtain desk/project identifiers.

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?

Specific verb+resource+scope: 'Delete files/folders (folders with all contents) on a project disk.' The parenthetical clarifies that folder deletion is recursive, and 'project disk' scopes the tool apart from generic file siblings.

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?

Prescribes the two-step protocol clearly: call once without confirm to preview, then repeat with confirm=true after user approval, and batch every path into one request. Lacks an explicit 'don't use this, use X instead' pointer, so it stops just short of a 5.

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