Skip to main content
Glama

NASC: Networked AI Session Continuity

nasc_live

Live sessions and exact capture status; advisory, never blocks an edit. board lists unclosed sessions, excluding the caller when session_id is given; captured marks that a first save was recorded at some point and is not current capture health, and last_saved_at is the newest saved turn. claim records a file touch; receipt returns the first-ingest receipt and the current status line; heartbeat is compatibility-only; clear ends presence.

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_live"
  }
}

Input Schema

NameRequiredDescriptionDefault
whoNoFallback operator name.
pathNoclaim: absolute file path.
brainNoOptional target org (brain uuid). Ignored unless this account can already access it; it never grants access.
actionYes
cc_sidNoOptional raw Claude Code session id.
statusNoDefault 'editing'.
projectNoProject slug.
session_idNoSession id from nasc_start. Required except for board.
continuity_tokenNoOptional host conversation id. Resolves the active session and pins this call's authorization, org and project to it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations at all, the description carries the full behavioral burden, and it does disclose several non-obvious traits: the tool is 'advisory, never blocks an edit', 'captured' is historical rather than current capture health, and 'clear ends presence'. That last point is a mutation with no stated reversibility, permission requirement, or confirmation behavior, and 'claim records a file touch' leaves unstated whether it overwrites or appends. The disclosure is above average for an unannotated tool but leaves side effects and authorization unaddressed.

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?

Every clause is front-loaded with value and the semicolon-delimited action list is scannable for an agent parsing per-action semantics. The one dense spot is the 'captured ... last_saved_at' clause, which packs two field definitions into a single run-on sentence, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a nine-parameter, five-action tool with no annotations and no output schema, so the description must carry the whole load. It covers what each action does and clarifies two confusing fields, but return payloads are only gestured at ('receipt returns the first-ingest receipt and the current status line') and there is no error or empty-state guidance for board. Adequate, with clear residual gaps.

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 89%, so the parameters are already well documented and the baseline is 3. The description contributes a genuine extra — that session_id additionally scopes board to exclude the caller — but adds nothing about status, project, cc_sid, or how the enum values interact with each action. It neither compensates for nor meaningfully extends the schema.

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 opening phrase 'Live sessions and exact capture status' names the resource, and the rest of the description enumerates each of the five actions (claim, board, receipt, heartbeat, clear) with a concrete verb-object gloss. An agent can tell this is the presence/session-liveness tool rather than a start/end tool, though the top-line phrase alone is noun-heavy and the real clarity comes from the per-action clauses.

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

Usage Guidelines3/5

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

The description gives strong in-tool routing cues — 'board lists unclosed sessions, excluding the caller when session_id is given' and 'heartbeat is compatibility-only' — which effectively says when not to bother calling an action. What is missing is cross-tool guidance: nothing indicates when to reach for this versus nasc_start, nasc_turn, or nasc_start_status, and the caveat 'advisory, never blocks an edit' only implies usage context. Guidance is implied per action but never explicit about selection among siblings.

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