Skip to main content
Glama
Sign In
littlebigbrains

@littlebigbrain/mcp

by littlebigbrains
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

lbb_embeddings_delete

DestructiveIdempotent

Delete an embedding by name and remove its vectors, making its class unsearchable until declared and rebuilt; destructive actions require client approval.

Instructions

Delete an embedding: its name and its vectors (index-gc removes the stored runs). Its class stops being searchable until it is declared and built again. The server asks the person to approve it through the client (MCP form elicitation) and sends nothing when they decline (approval_declined). A client that cannot show the question gets approval_required and nothing is sent, unless the MCP server's environment sets LBB_MCP_DESTRUCTIVE=allow.

Input Schema

NameRequiredDescriptionDefault
nameYesThe embedding name.
graphNoGraph to target; defaults to the connection's graph
detailNoResponse detail level. Defaults to compact.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.16.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / confirm
      Removed value: -{
-  "description": "The same name again, to confirm.",
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "name",
-  "confirm"
-]New value: +[
+  "name"
+]
  2. Addedv0.5.2

TDQS

A4.1/5.0
Behavior5/5

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

Well beyond the annotations, which only flag destructive/idempotent: the description discloses what is irreversibly destroyed, the searchability consequence afterward, the human-approval gate via MCP form elicitation, the two failure outcomes (approval_declined sends nothing, approval_required sends nothing), and the LBB_MCP_DESTRUCTIVE=allow environment escape hatch. This is exactly the context an agent needs before invoking 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 destructive action and its scope, then the consequences, then the approval mechanics. Three sentences carry a lot of distinct information with little waste, though the final sentence stacks two error codes plus an environment variable and reads slightly dense.

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?

Given a 3-parameter schema, no output schema, and destructive annotations, the description covers the action, side effects, approval flow, and failure modes thoroughly. The only gap is the response shape — nothing indicates what a successful delete returns or how 'detail' affects it — which is a minor omission for a delete tool.

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%, with all three parameters documented including the detail enum and the graph default, so the schema carries the parameter burden. The description adds no parameter-level meaning — it does not explain what 'graph' or 'detail' mean in the delete context — so the baseline 3 applies.

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 ('Delete an embedding') and goes further to enumerate exactly what is removed: the name, the vectors, and the stored runs via index-gc. It also describes the post-condition ('Its class stops being searchable until it is declared and built again'), which an agent could not infer from the name alone.

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 makes clear this is a destructive, approval-gated operation and explains what happens in the decline/unavailable-client branches, which is real usage context. However, it never routes the agent between this tool and siblings like lbb_embeddings_manage or lbb_embeddings — there is no explicit 'use this when you want to remove, use that to modify' statement.

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