Skip to main content
Glama
avaazquezz

io.github.avaazquezz/mcp-qdrant

by avaazquezz

qdrant_points_delete

DestructiveIdempotent

Deletes Qdrant points by explicit IDs or a payload filter, requiring exactly one selector. Use it to remove matching vectors and their payloads from a collection.

Instructions

Delete points by id list or by payload filter — exactly one of the two.

    Deleting an id that doesn't exist is not an error (Qdrant treats it as
    a no-op); this only fails if the collection itself is missing, or if
    you provide zero or both selectors.

    Example (by id): {"collection_name": "docs", "ids": [1, 2]}
    Example (by filter): {"collection_name": "docs", "points_filter": {
        "must": [{"key": "city", "match": {"value": "ny"}}]
    }}
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idsNo
points_filterNo
collection_nameYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusYes
operation_idNoSequential number of the operation

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv1.1.1

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotation's destructive/idempotent hints, the description adds valuable behavior: deleting a nonexistent id is a no-op and the only failure modes are a missing collection or zero/both selectors. It does not spell out that a filter deletes all matching points, but annotations already cover the destructive profile.

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?

The description is front-loaded with the core purpose, and every subsequent sentence adds meaningful constraint or failure-mode detail. The two examples are compact and directly illustrate both supported selector modes.

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 destructive delete tool with a complex filter schema and an output schema present, the description covers the essential selector exclusivity, example payloads, and failure cases. A minor gap is not explicitly stating that a filter selection deletes all matching points, though that is strongly implied.

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?

With 0% schema description coverage for the parameters, the description compensates by explaining the two selectors, requiring exactly one, and providing concrete JSON examples for both ids and points_filter. collection_name is shown in examples but not independently described; the rich Filter schema fills in the remaining structure.

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 leads with a specific verb and resource: 'Delete points by id list or by payload filter'. It also scopes the operation with 'exactly one of the two', which clearly distinguishes the two deletion modes and separates it from sibling read/upsert tools.

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?

The description gives clear operational context and constraints (exactly one selector, needs an existing collection) but never names alternatives or says when not to use this tool, such as preferring qdrant_collection_delete for whole-collection deletion. Usage is therefore implied rather than explicitly contrasted with siblings.

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

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/avaazquezz/Qdrant-MCP'

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