Skip to main content
Glama

NASC: Networked AI Session Continuity

nasc_session_cleanup

Organization admin cleanup of stale exact sessions; nasc_end stays self-only. get_policy reads the role threshold; set_policy (owner only) sets disabled or a minimum role. preview takes exact session ids, checks role, age, turns, lifecycle and presence, and returns a short-lived receipt. execute takes only that receipt, rechecks every target in one transaction, soft-closes them with no digest or handoff, writes an audit receipt and notifies each affected operator. Guests and cross-organization grants never have session authority. override_min_age with override_reason lets a platform superadmin bypass only the age gate.

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": {
      "action": "<action>"
    },
    "name": "nasc_session_cleanup"
  }
}

Input Schema

NameRequiredDescriptionDefault
brainNoOptional target org (brain uuid). Ignored unless this account can already access it; it never grants access.
actionYes
min_roleNoset_policy: minimum direct role, or disabled.
session_idNoOptional session id from nasc_start. Pins this call's authorization, org and project to that session.
session_idsNopreview: exact session UUIDs. Cleanup never searches by age, platform, name or project.
override_reasonNopreview: human-authorized reason, kept in the audit receipt.
continuity_tokenNoOptional host conversation id. Resolves the active session and pins this call's authorization, org and project to it.
override_min_ageNopreview: superadmin age-gate override; requires override_reason. Other checks remain.
preview_receipt_idNoexecute: unexpired receipt from preview.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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: preview's checks (role, age, turns, lifecycle, presence), execute's transactional recheck, soft-close with no digest or handoff, audit receipt write, and operator notifications. It also discloses the receipt's short lifetime and that override_min_age bypasses only the age gate while all other checks remain — exactly the mutation-risk context an agent needs.

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?

Purpose is front-loaded and almost every clause carries operational content, but the prose is a dense semicolon-chained run-on that would read faster as a short action list. Nothing is truly wasted, though the packing hurts scannability.

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 9-parameter, four-action mutation tool with no annotations and no output schema, the definition covers sequencing, permissions, side effects and receipt lifetime well. The one gap is return-shape detail for get_policy and set_policy, which the absence of an output schema leaves unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 89%, so the baseline is 3. The description adds real meaning on top by binding parameters to actions (session_ids for preview, preview_receipt_id as the sole execute input) and by explaining that override_min_age depends on override_reason and is limited to the age gate. It adds little for brain, session_id or continuity_token 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?

States a specific verb and resource — organization admin cleanup of stale exact sessions — and immediately scopes it against the sibling: 'nasc_end stays self-only.' The 'exact sessions' qualifier plus the follow-up that cleanup never searches by age, platform, name or project makes the boundary unambiguous.

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

Usage Guidelines5/5

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

Lays out the four-action workflow with the conditions that select each: get_policy reads the threshold, set_policy is owner-only, preview validates and issues a receipt, execute consumes only that receipt. It also names the alternatives and gates (nasc_end for self-only, platform superadmin for the age override, guests and cross-org grants excluded), leaving nothing to inference.

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