Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

set_autonomy_level

Destructive

Set the agent's autonomy tier to control tool approval: 0 confirms all, 1 pre-screens within constraints, and 2 allows all except emergency-level tools.

Instructions

Set the autonomy tier (0, 1, or 2).

Level 0 (Confirm All): Every confirm-level tool requires approval.
Level 1 (Pre-screened): Confirm-level tools allowed if constraints pass.
Level 2 (Full Trust): All tools allowed except emergency-level.

Changing this updates the config file.  Requires human confirmation
because it affects how much control the agent has.
:param level: The tier to set: ``0`` confirm all, ``1`` pre-screened,
    ``2`` full trust.

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": {
      "level": "<level>"
    },
    "name": "set_autonomy_level"
  }
}

Input Schema

NameRequiredDescriptionDefault
levelYesThe tier to set: ``0`` confirm all, ``1`` pre-screened, ``2`` full trust.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.5.1
    • addedInput schema / properties / level / description
      Added value: +"The tier to set: ``0`` confirm all, ``1`` pre-screened, ``2`` full trust."
  2. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already flag a destructive, non-read-only mutation, and the description adds meaningful context beyond them: it persists to the config file and requires human confirmation because it changes agent control. It does not say what the confirmation flow looks like or what the response contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The tier table is front-loaded and readable, but the final ':param level:' block is a Sphinx artifact that duplicates the schema and could be cut. The middle paragraph is well placed and earns its space.

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 single-parameter config mutation with no output schema, the description covers what changes, where it is persisted, and that human confirmation is required. Missing only details of the confirmation mechanism and any return value.

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 100% and the trailing ':param level:' text repeats the schema's parameter description nearly verbatim, adding no new meaning. The tier explanation is useful for understanding consequences but is already mirrored in the schema's enum text.

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?

States a specific verb+resource ('Set the autonomy tier') and enumerates the three values with their names and semantics. It is clearly distinct from the sibling get_autonomy_level, though that distinction is carried by the verb alone rather than stated explicitly.

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?

The level semantics implicitly tell the agent what each tier means, but there is no explicit guidance on when to raise or lower the tier, prerequisites, or what to do instead if settings should be read rather than changed. Usage is inferable rather than instructed.

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