Skip to main content
Glama

Remove a workspace model key

remove_model_key
DestructiveIdempotent

Delete a shared Anthropic or OpenRouter API key from this workspace. Tasks depending on that key may lose model access. Workspace admins or owners only. Never supply the key itself.

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": {
      "workspace_id": "<workspace_id>",
      "provider": "<provider>"
    },
    "name": "remove_model_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
providerYes
workspace_idYesThe workspace id (from whoami).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds value beyond that: it discloses the downstream impact on dependent tasks, the admin/owner authorization requirement, and a security constraint ('Never supply the key itself'). It does not clarify whether the key is revoked for all consumers or only unlinked from this workspace, which is the main remaining behavioral question.

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 followed by consequence, authorization, and security constraints in descending order of importance. No sentence is redundant and nothing is buried.

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 two-parameter destructive mutation with no output schema, the description covers the essentials: what is deleted, who may do it, what breaks, and what not to pass. The one gap is the meaning of 'shared' — whether removal affects other workspaces or consumers of the key — which matters for a destructive operation.

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 coverage is 50%: workspace_id is documented in the schema and provider is an enum whose values are self-explanatory. The description does reinforce the provider values ('Anthropic or OpenRouter') and, via 'Never supply the key itself,' clarifies that the key is identified by provider rather than by a secret argument. That is useful but marginal, so baseline 3 is appropriate.

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?

The description opens with a specific verb and resource ('Delete a shared Anthropic or OpenRouter API key from this workspace'), which is precise enough that an agent can tell it apart from list_model_keys or model_key_settings. It stops short of naming a sibling or stating the inverse operation explicitly, so it lands just under 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?

'Workspace admins or owners only' gives a permission precondition and 'Tasks depending on that key may lose model access' gives a consequence, which together imply when this tool is appropriate. However, there is no explicit when-to-use versus alternatives guidance (e.g., rotating a key versus deleting it, or clearing a default versus removing the key), leaving the trigger condition to inference.

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