Skip to main content
Glama

Update settings

update_settings
Idempotent

Change selected app settings by passing only the keys you want altered; unspecified preferences stay unchanged. Use the separate AI provider tool for model changes.

Instructions

Change app settings; only the keys you pass change. Use set_ai_provider for the AI provider/model.

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": {
      "settings": "<settings>"
    },
    "name": "update_settings"
  }
}

Input Schema

NameRequiredDescriptionDefault
settingsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.3
    • addedInput schema / properties / settings / properties / checkHour
      Added value: +{
      +  "description": "Local hour (0-23) automatic checks start at; null spreads them across the day.",
      +  "maximum": 23,
      +  "minimum": 0,
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
  2. First observedv0.1.7

TDQS

A3.9/5.0
Behavior4/5

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

The annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the bar is lower. The description adds genuinely new semantics beyond them: mutation is a partial merge in which "only the keys you pass change," so omitted settings are preserved rather than defaulted — the single most important behavior for a bulk settings object. It says nothing about validation failures or atomicity if one key is invalid.

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?

Two clauses, both front-loaded: the action and its partial-update semantics come first, the sibling redirect second. No filler, no repetition of the title or of schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool over a large, nested settings object with no output schema, the definition covers the essentials (what changes, what is preserved, where the AI provider goes) but omits error behavior, whether the whole patch is rejected when one value is out of range, and what is returned after the update. Those gaps matter for a 20-plus-key write tool, though the schema's enums and min/max limits offset some risk.

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?

The tool exposes one required nested `settings` object whose individual keys carry rich in-schema descriptions and enums, so most meaning already lives in the schema. The description's contribution is the merge/partial-update rule, which the schema does not state, but it does not clarify required-vs-optional key groups or what happens with unknown keys. 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 gives a specific verb plus resource ("Change app settings") and immediately carves out the AI provider/model case to a named sibling. It does not enumerate which settings are covered, but an agent can still tell what this tool mutates and how it differs from set_ai_provider.

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

Usage Guidelines4/5

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

It explicitly routes one case elsewhere ("Use set_ai_provider for the AI provider/model"), which prevents a likely mis-call given update_settings also touches aiEffort/aiFallback. It stops short of stating conditions like when a full reset or per-project override is preferable to a partial patch.

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