Skip to main content
Glama

NASC: Networked AI Session Continuity

nasc_org_settings

Per-org Control Panel settings for the active brain. read (default) returns the assembled posture: org_settings, the connected-tool registry with train-by-tier and vendor policy, and plan and retention. set writes posture keys; clear restores defaults. Billing fields are display-only. set and clear require a super-admin or an owner of this brain, enforced server-side, and never write another tenant's brain or a non-posture key.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "nasc_org_settings"
  }
}

Input Schema

NameRequiredDescriptionDefault
whoNoOperator name label. Attribution comes from the authenticated account.
actionNoDefault 'read'.
presetNoDisplay-only grouping.
providersNoPer-provider {capture, privacy} map; display only.
live_scopeNoOrg default live-board scope, fallback only.
capture_pointsNoOpaque blob; display only.
overage_policyNoDisplay only until billing enforcement.
unrouted_notifyNoWho hears about captures parked in the holding pen. Default intaker, their owner. admins tells org owners instead and is opt-in because it reveals who holds unfiled conversations; both tells both; off hides it.
grant_notify_scopeNoReach of a cross-org grant visitor's notify send. Default project: the shared project's people and the grantor, never a broadcast. org: any named member; all: broadcasts; off: no grant sends. Members are unaffected.
agent_spend_cap_usdNoUSD, non-negative; display only.
search_scope_defaultNoOrg default search scope, fallback only.
dev_self_serve_cap_usdNoUSD, non-negative; display only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses the authorization model (super-admin or owner, enforced server-side), blast-radius constraints (never writes another tenant's brain or a non-posture key), that clear restores defaults, and that billing-related fields are display-only. What it omits is the failure mode (what happens on an unauthorized set or an unknown key) and rate/response characteristics.

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?

Three dense sentences, front-loaded with the resource and the read/set/clear triad, then the permission and isolation guardrails. Every clause carries information and there is no filler, though the middle sentence packs several distinct concerns together at the cost of some scanability.

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 12-parameter tool with a nested object, no annotations and no output schema, the definition covers the essentials: what read returns (org_settings, connected-tool registry with train-by-tier and vendor policy, plan and retention), what set and clear mutate, and who may do it. The absence of an output schema is partly compensated by that enumeration; the remaining gap is that posture-vs-display-only key membership is never enumerated.

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 description coverage is 100%, so the baseline is 3. The description does add real meaning beyond the schema by scoping set to 'posture keys' only, which implies the many display-only fields (preset, providers, capture_points, billing caps, overage_policy) are not writable, but it does not name which keys count as posture, leaving that inference to the caller.

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 names a specific resource (per-org Control Panel / posture settings for the active brain) and enumerates the three actions it performs: read, set, clear. An agent can tell what the tool governs without opening the schema. It stops short of distinguishing itself from a similarly-scoped sibling such as nasc_preferences, which costs it a point.

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?

Usage is spelled out per action: read is the default and returns the assembled posture, set writes posture keys, clear restores defaults, and set/clear require super-admin or brain-owner rights. That is clear contextual guidance for choosing an action. It never states when to prefer a sibling tool over this one or when not to use it, so it falls short of explicit alternatives.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources