Skip to main content
Glama

NASC: Networked AI Session Continuity

nasc_end

Closes the caller's own NASC session and writes its digest, including the handoff the next start reads. Digest fields are optional; synthesis writes what is absent. This tool closes a session only for its owner or a platform administrator; a continuity token or alias locates a session but does not prove ownership, and a session with an unresolved owner stays open. soft=true closes without a digest, which suits stale or trivial sessions. Closing a session that already has its full digest changes nothing. A managed Window full close reports capture_status=final_pending and final_capture_receipt=false until its final exchange is acknowledged; transcript_captured only indicates whether earlier transcript data was already stored. On Codex Desktop and Codex CLI a close with no session_id and no continuity_token returns a queued handoff receipt; digest fields remain optional. A successful close returns structured JSON, then a Markdown receipt that begins NASC SESSION ENDING (pending) or NASC SESSION ENDED. Another person's stale session is closed by an organization administrator with session_cleanup.

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_end"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostNoOptional host platform as passed to nasc_start, inferred from the MCP client when omitted. On codex_desktop or codex_cli an unkeyed full close returns a queued handoff receipt.
nextNo
softNoEnds the exact session with no digest, changelog entry or wiki snapshot; digest fields are ignored. Requires session_id under session keying.
tldrNoOptional one-line handoff, 200 characters or less.
brainNoOptional target org (brain uuid). Ignored unless this account can already access it; it never grants access.
projectNoProject slug.
summaryNoOptional. What this session did.
rejectedNo
resolvedNoOptional decision keys (decision:<id>) this session finished; each is marked done when this session or its person holds the claim. Ignored on soft=true, which only parks. Other items this session was carrying in doing are parked, not closed.
bugs_fixedNo
bugs_foundNo
notify_whoNo
session_idNoOptional session to close, from nasc_start; only its turns join the digest.
source_uriNoSource conversation URI or id, when known.
fields_sentNoOptional comma-separated names of the arguments this call carries.
files_changedNo
decisions_madeNo
source_platformNoPlatform the content came from.
context_for_nextNoOptional handoff the next session inherits.
continuity_tokenNoOptional host conversation id. Resolves the active session and pins this call's authorization, org and project to it.
capture_terminal_idNoTranscript ingester only.
require_exact_digest_replayNoOptional strict idempotency check for Scribe. When true, supplied nonblank summary, context_for_next and tldr must match the stored digest exactly. Grants no authority.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
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: it explains authorization, unresolved-owner behavior, idempotency, soft-close semantics, Codex-specific queued handoff behavior, and the returned JSON plus Markdown receipt. These are material behavioral details beyond the schema.

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?

The description is front-loaded and dense, appropriate for a 22-parameter close tool with no annotations. It repeats that digest fields are optional in two places, which is minor waste but does not obscure the main guidance.

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 mutation tool with no annotations and no output schema, the description covers the critical behavioral context: ownership, soft close, idempotency, receipt format, and the session_cleanup alternative. Some parameter-level detail remains in the schema, and a few low-coverage parameters are not elaborated.

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?

The schema has 22 parameters and only 68% description coverage, so the description must compensate for some gaps. It adds useful meaning for digest fields, soft=true, and continuity_token ownership semantics, but many array and metadata parameters are left to the schema.

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 opens with a specific verb and resource: it closes the caller's NASC session and writes the digest/handoff. It also distinguishes this tool from the sibling alternative for another person's stale session by naming session_cleanup.

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?

It gives explicit conditions for use: ownership and administrator rules, soft=true for stale or trivial sessions, and no-op behavior when the digest is already complete. It names the alternative path for another person's stale session, so an agent can route correctly.

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