Skip to main content
Glama
Sign In

Nebelus

by ai.nebelus.api
OverviewDiscussionsAdmin

Update governance policy

update_governance_policy

Edit an existing policy: name, description, severity, which side it checks (validation_points) or individual configuration keys (configuration_patch, merged into what is stored). Does not activate or deactivate; editing an ACTIVE policy changes live enforcement.

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": {
      "policy_id": "<policy_id>"
    },
    "name": "update_governance_policy"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoNew name.
severityNoPolicy severity.
policy_idYesId of the policy (from get_catalog view=policies).
descriptionNoNew description.
validation_pointsNoWhich side the policy checks: input = messages users send, output = replies the agent writes, both (default when unset). Only for data_privacy, content_filter, output_validation, custom.
configuration_patchNoConfiguration keys to change; unnamed keys are kept.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / policy_id / description
      Previous value: -"Id of the policy (from list_policies / get_catalog)."New value: +"Id of the policy (from get_catalog view=policies)."
  2. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description adds real value on top: it clarifies the tool never flips activation state and that editing an ACTIVE policy alters live enforcement. That said, it says nothing about permissions/authorization requirements, whether a partial edit is atomic, or what happens when a configuration key is invalid, which are the meaningful unknowns for a non-destructive mutation.

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?

Two sentences, no filler, and the core capability is front-loaded before the caveats. The compression is slightly aggressive ('which side it checks (validation_points)', the slash-free field list), but nothing is wasteful and the important constraint is placed last for emphasis.

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 6-parameter mutation with no output schema, the description covers scope, the non-activation guarantee, and live-enforcement impact — enough to call it safely. Remaining gaps are authorization expectations and error behavior, which are secondary for an agent that already has full schema coverage and annotations.

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%, so every parameter already carries its own description, including the validation_points semantics and the merge behavior of configuration_patch ('unnamed keys are kept'). The description's phrase 'which side it checks' and 'merged into what is stored' restates rather than extends that, so the baseline of 3 applies.

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 sentence opens with a specific verb+resource ('Edit an existing policy') and enumerates the editable fields (name, description, severity, validation_points, configuration_patch). It explicitly distinguishes itself from the activation siblings with 'Does not activate or deactivate', so an agent can separate it from activate_governance_policy and create_governance_policy immediately.

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 exclusion clause routes activation/deactivation work to the sibling tools, and the note about editing an ACTIVE policy changing live enforcement tells the agent when this call has production impact. It stops short of naming a concrete alternative tool or spelling out prerequisites, so it is strong context rather than a full when/when-not routing rule.

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

All Nebelus toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources