Skip to main content
Glama

NASC: Networked AI Session Continuity

nasc_start

Opens a NASC session for the authenticated account in a resolved organization and project. An exact accessible project opens directly. A non-exact name returns confirmation_required with suggestions and opens nothing; a retry with a suggestion's arguments follows only the human's explicit choice. Without a project, the result offers an organization or project picker. A successful start returns the session id immediately in compact JSON and a bounded canonical text landing. Capture attachment follows separately.

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_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
osNoOptional advisory OS hint.
tzNoOptional. The operator's IANA timezone, read from the host clock at call time (Intl.DateTimeFormat().resolvedOptions().timeZone). Feeds the landing's time_anchor and the stored display default; without it, times show in the stored default or labeled UTC.
ansiNoIgnored; kept for compatibility.
hostNoOptional host platform (claude_ai, cursor, claude_code...), inferred from the MCP client when omitted. Scopes the capture health check.
nextNo
brainNoOptional target org (brain uuid). Ignored unless this account can already access it; it never grants access.
threadNoOptional open_threads digest id from a prior landing; its handoff becomes prior_handoff. Project-fenced; an unknown id falls back to the default.
machineNoOptional hostname read at call time (`hostname` or $env:COMPUTERNAME); scopes Scribe health to this machine. A remembered or guessed value gives a false 'no Scribe' answer.
pick_upNoOptional open-item keys (decision:<id>, as in open_loops[].key) started on this session. An item in flight under another person's live session is never overtaken here and returns as contested; nasc_preferences pick_up with confirm is the deliberate mid-session takeover.
projectNoProject slug. When omitted, the result offers a picker; a previous session never picks the project.
blockersNo
selectionNoIdentity guard from a startup suggestion, sent back exactly as returned after the human chooses. It grants no access and is not consent.
organizationNoOptional exact organization name or slug, for a project that matches more than one organization or after organization_required.
current_focusNoOptional focus for the project's now register.
open_questionsNo
continuity_tokenNoLegacy capture adapter token. Current native and web starts omit it; a supplied token resumes the session already bound to it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: immediate session id in compact JSON, a bounded text landing, confirmation_required on ambiguous names, contested open-items that are never overtaken, and that brain/selection never grant access. It does not cover side effects, idempotency, auth requirements, or failure modes beyond the picker/confirmation branches, so it is good but not complete for a session-mutating tool.

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 first sentence front-loads purpose and the subsequent sentences walk the outcome branches in order, with no filler. Some phrasing is heavy jargon ("bounded canonical text landing," "capture attachment follows separately") that costs clarity without adding much.

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 16-parameter, no-annotation, no-output-schema tool, the description covers the return shape, the confirmation/picker branches, and the access boundaries that matter most. Remaining gaps (what the next/blockers/open_questions arrays feed, what the landing text contains) are largely handled by the high-coverage schema.

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 81%, so the schema already documents nearly every parameter, including the subtle ones (tz, machine, thread, selection, continuity_token). The description adds nothing parameter-specific beyond "retry with a suggestion's arguments," so the baseline 3 applies.

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 states a specific verb and resource ("Opens a NASC session for the authenticated account in a resolved organization and project") and explains the resolution semantics of organization/project. It distinguishes itself from nasc_preferences pick_up for the takeover case, though it never explicitly contrasts with nasc_start_status or nasc_intake, which an agent could plausibly confuse with a session-start operation.

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?

It gives concrete operating guidance: a non-exact project name returns confirmation_required and opens nothing, and the retry must follow only the human's explicit choice; with no project the result offers a picker. What's missing is an explicit "use this rather than X" statement for the obvious sibling alternatives and any note on prerequisites such as prior session state.

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