Skip to main content
Glama

Delete a model you saved

delete_graph
DestructiveIdempotent

Deletes one graph you saved, together with the runs of it. Use this when the user has explicitly asked for that model to be removed, and not otherwise. Confirm which one first with list_graphs or get_graph, because the graph_id is the only thing that says which model goes. Neumann purges it for good after 30 days, and until then nothing on this connector can restore it -- no tool here can put it back -- so treat it as final and do not tell the user it can be recovered. Deleting the same graph twice changes nothing and does not extend the 30 days. To stop using a graph without removing it, just leave it saved and do not pass its graph_id. It returns the graph_id, what kind of thing was deleted, the time it was deleted and the date it is purged for good. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "graph_id": "<graph_id>"
    },
    "name": "delete_graph"
  }
}

Input Schema

NameRequiredDescriptionDefault
graph_idYesWhich saved graph to delete, from list_graphs. Its runs go with it. Confirm with the user first: no tool here can put it back.

Output Schema

NameRequiredDescriptionDefault
kindNoWhat kind of thing was deleted: a graph.graph
billingNoWho you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today.
graph_idYesThe id of the graph that was deleted.
deleted_atYesWhen it was deleted, as an ISO-8601 time.
purge_afterYesThe ISO-8601 instant after which it is removed for good. Until then it is recoverable inside Neumann, but not by any tool here.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, but the description adds substantial context beyond them: a 30-day purge window, that nothing on the connector can restore it, that no tool can put it back, and that repeated deletion does not extend the window. It also discloses authentication requirements (Bearer credential in the Authorization header, no api_key argument, anonymous callers get authentication_required) and cost behavior (free, no credits debited).

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?

The critical constraints (explicit user request, confirmation first, irreversible) are front-loaded, which is the right ordering for a destructive tool. It is somewhat long and repeats the irreversibility point ('nothing on this connector can restore it -- no tool here can put it back' also appears in the schema), but nearly every sentence carries operational weight.

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 single-parameter destructive mutation, the definition covers scope, precondition, confirmation path, irreversibility, idempotency, auth, cost, and even return contents despite an output schema existing. There is no gap an agent would need to guess at before calling.

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 100% and the schema itself carries an example and a warning, so the baseline is 3. The description adds real meaning on top: graph_id is the sole identifier of which model is destroyed and should be confirmed with the user first, which is decision-relevant information rather than a restatement.

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 first sentence names a specific verb and resource ('Deletes one graph you saved, together with the runs of it'), and the definition explicitly positions itself against list_graphs and get_graph as read-only identifiers. An agent can tell what this tool does and what it does not do with no ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states a hard precondition ('when the user has explicitly asked for that model to be removed, and not otherwise'), names the tools to use first to confirm the target, and supplies an explicit non-delete alternative ('just leave it saved and do not pass its graph_id'). This is about as complete as when-to-use guidance gets.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources