Skip to main content
Glama

Settings Set

settings_set
Destructive

Change any report, page or component panel setting through the editor's own bindings in one journalled write, with dry-run preview, read-back verification and undo support.

Instructions

Change any editor panel settings natively, in one journalled write.

Keys and value shapes come from settings_describe (value = what describe shows, an option's value for dropdowns). Changes apply in order through the editor's own bindings, so dependent settings follow as in the UI; theme settings on a built-in theme first copy it into the report's custom theme (as Customize does). Only the resulting native delta is written over the saved content; read-back verified; operation_restore undoes it. dry_run previews before/after without writing.

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": {
      "target": "<target>",
      "changes": "<changes>",
      "expected_fingerprint": "<expected_fingerprint>"
    },
    "name": "settings_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
targetYesWhat owns the panel: the report, a page, or a component (any depth) on a page.
changesYes
dry_runNo
report_idNo
expected_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations, which already mark this as mutating and destructive, the description discloses that writes are journalled, changes apply in order through editor bindings, dependent settings follow, built-in theme edits first create a custom theme copy, only the native delta is written, results are read-back verified, and operation_restore can undo the write.

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?

The description is front-loaded with the core purpose and then adds only operationally useful details. Each sentence carries specific information about source of keys, application order, theme handling, write behavior, verification, undo, and previewing.

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 complex, destructive settings mutation tool with nested parameters, the description covers the important behavioral edges: journalled writes, dependency propagation, theme copying, delta-only persistence, verification, undo, and dry-run preview. The main omission is the role of expected_fingerprint, which is required but not explained anywhere in the description.

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?

With only 20% schema description coverage, the description adds important meaning for the changes parameter by explaining that keys come from settings_describe and that values should match what describe shows, including option values for dropdowns. However, it does not explain the required expected_fingerprint parameter, nor does it add much about target/report_id semantics beyond what the schema already says.

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 description states a specific verb and resource: "Change any editor panel settings natively, in one journalled write." It also distinguishes the tool from settings_describe by saying keys and value shapes come from that sibling, and from operation_restore by naming it as the undo mechanism.

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?

The description gives clear operational guidance: use settings_describe for keys and value shapes, use operation_restore to undo, and use dry_run to preview. It does not explicitly say when to prefer settings_set over settings_set_batch, so there is a small gap in alternative selection guidance.

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