Skip to main content
Glama

NASC: Networked AI Session Continuity

nasc_triage

Retires outdated memory from live context. list returns this project's session digests with status and age. gray marks an item by kind and id (session digest, wiki node, work-log line or doc): it stays searchable and in history but leaves live recall and the cold-start handoff; ungray reverts it. Gray is a reversible label, not a deletion. For decisions, retire archives one with a before-image, supersede points it at an existing newer decision, and reinstate undoes either. set_reconciler attaches a wiki page's reconciler declaration; clear_reconciler removes it. Decision and reconciler actions are human-directed and require evidence, the human directive being carried out; synthesis never sets a reconciler. Permanent deletion is a human-only Control Panel action and is never available to this tool.

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_triage"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNouuid for session_digest, wiki and doc; integer for work_log and decision.
whoNoOperator name label. Attribution comes from the authenticated account.
kindNogray/ungray default session_digest. Decision actions use decision; reconciler actions use wiki (both defaulted).
brainNoOptional target org (brain uuid). Ignored unless this account can already access it; it never grants access.
limitNolist: 1-50, default 20.
actionYes
statusNolist: filter.
projectNoProject slug.
evidenceNoRequired for decision and reconciler actions: the human directive or observation carried out, 500 chars max. Stamped into provenance.
reconcilerNoRequired for set_reconciler: artifact (where truth lives), check (the exact question to ask it), refutes_when (the answer that refutes the page). Non-empty, 500 chars max each.
session_idNoOptional session id from nasc_start. Pins this call's authorization, org and project to that session.
superseded_byNosupersede: id of the existing newer decision.
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

A4/5.0
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 largely discharges it: it discloses the effect of gray (stays searchable and in history but leaves live recall and the cold-start handoff), reversibility via ungray, that retire keeps a before-image and supersede/reinstate form an undo pair, and that synthesis never sets a reconciler. These are exactly the side-effect and authorization facts an agent needs before invoking a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Proportionate in length for eight actions and front-loaded with the core purpose, but it is delivered as one undifferentiated run-on paragraph. An agent scanning for a specific action must parse every sentence to locate the clause that governs it; grouping by action would have made this materially easier without adding words.

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 13-parameter tool with a nested object, no annotations, and no output schema, the description covers all eight actions and the main safety and evidence constraints. It says list returns session digests with status and age, but leaves the return shape of retire, supersede, and the reconciler actions unspecified, which is a modest gap given there is no output schema to fall back on.

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 92%, so the schema already documents id typing, kind defaults, limit ranges, evidence requirements, and the reconciler object. The description adds only marginal meaning beyond that, chiefly the rule that synthesis never sets a reconciler. Baseline 3 is appropriate when the schema does this much of the work.

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?

Opens with a specific verb and resource ("Retires outdated memory from live context") and then enumerates every action the tool performs, including the crucial distinction that gray is a reversible label rather than a deletion. The gap is sibling differentiation: nothing here tells an agent how this differs from nasc_session_cleanup or nasc_wiki, both of which plausibly overlap with the gray/retire surface.

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?

Gives per-action guidance ("For decisions, retire archives one with a before-image, supersede points it at an existing newer decision, and reinstate undoes either") plus an explicit exclusion: permanent deletion is human-only and never available here. It also states decision and reconciler actions are human-directed and require evidence. It stops short of naming a sibling tool as the alternative when this one is the wrong choice.

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