Skip to main content
Glama

Update a deployed endpoint's config

update_endpoint
Destructive

Change a deployed endpoint's settings in place—auth mode, enabled state, allowed verbs, scopes, notes—without redeploying. Preview changes first, then confirm to apply.

Instructions

Updates a deployed endpoint's config in place — isMain, isEnabled, allowedVerbs, detailedOutput, isAnonymous, authMode, requiredScopes and/or notes — without a full redeploy. Only the fields you pass are changed; omit the rest. authMode decides who may call it: anonymous, apiKey, user (a visitor signed in to the site), jwt (a token from one of the domain's API clients — create_domain_client — or a trusted issuer — set_trusted_issuer), apiKeyOrJwt. Powerful (can change security posture, e.g. isAnonymous, or take live traffic down via allowedVerbs/isEnabled): requires confirm=true — first call WITHOUT confirm to preview the exact changes, then again with confirm:true.

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": {
      "endpointId": "<endpointId>"
    },
    "name": "update_endpoint"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNo
isMainNoMake this the main version for its path.
confirmNoMust be true to apply. Omit/false returns a preview only.
authModeNoWho may call it. Wins over isAnonymous when both are sent.
isEnabledNoEnable/disable — same effect as toggle_endpoint but to a specific state.
endpointIdYesThe endpoint's id — from list_endpoints.
isAnonymousNo
allowedVerbsNo
detailedOutputNo
requiredScopesNoSpace-separated scopes a jwt / apiKeyOrJwt token must ALL carry, e.g. "orders:read". "" clears.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only carry destructiveHint=true; the description adds the substantive risk detail: it can change security posture (isAnonymous, authMode) and take live traffic down (allowedVerbs/isEnabled), which is exactly the blast-radius information the hint alone doesn't convey. It also discloses the preview-then-confirm safety flow and that updates are in-place rather than a redeploy.

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 what changes and the partial-update rule, then risk, then the confirm protocol in a logical order. The field list and parenthetical asides make it dense to the point of being slightly hard to scan, but no sentence is redundant.

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 10-parameter destructive mutation with only partial schema coverage and no output schema, the description covers mutability, risk, auth semantics and the confirm gate — enough for correct invocation. It stops short of describing what the preview response contains or how requiredScopes interacts with authMode when both are set.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

At 60% schema coverage the description compensates well by explaining the authMode enum values in prose (anonymous, apiKey, user = a visitor signed in, jwt = domain-client or trusted-issuer token, apiKeyOrJwt) and by qualifying the risk profile of isAnonymous and allowedVerbs. Remaining gaps are minor (notes, detailedOutput are named but not elaborated).

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+resource ('Updates a deployed endpoint's config in place') and enumerates the mutable fields, immediately distinguishing it from deploy_endpoint ('without a full redeploy') and from toggle_endpoint ('same effect as toggle_endpoint but to a specific state' via the schema). An agent can identify the tool's job without opening the schema.

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?

Gives explicit operational guidance: partial-update semantics ('Only the fields you pass are changed; omit the rest') and a two-step confirmation protocol ('first call WITHOUT confirm to preview the exact changes, then again with confirm:true'). It also points to create_domain_client and set_trusted_issuer as the sources of jwt auth material, so the agent knows where prerequisites come from.

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