Skip to main content
Glama

NASC: Networked AI Session Continuity

nasc_decisions

Canonical Decisions and Open Items. Every Open Item is a Decision; not every Decision is an Open Item. list and get read. create makes a decision-backed Open Item only on an explicit human request, requires human_requested=true, and checks for duplicates. The other actions are lifecycle verbs; pick_up, put_down and resolved are legacy aliases for start, park and complete.

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_decisions"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNodecision:<id>. Required for get and lifecycle writes.
whoNoOperator name label. Attribution comes from the authenticated account.
brainNoOptional target org (brain uuid). Ignored unless this account can already access it; it never grants access.
limitNolist: 1-100. Default 25.
queryNolist: title filter.
titleNocreate: title, 1-400 chars.
actionYes
detailNocreate: question or work detail, 1-50000 chars.
confirmNoclaim/start: allows taking over a live claim when authorization permits.
contextNocreate: optional context.
projectNoProject slug.
assigneeNoDefaults to self; assign requires a person name or alias.
reasoningNocreate: optional human rationale.
resolutionNocomplete: optional note.
session_idNoOptional active session. Writes inherit its project; claim and start attach to it.
confirm_newNocreate: confirms a distinct item after duplicate candidates.
include_doneNolist: include completed. Default false.
initial_statusNocreate. Default open.
candidate_tokenNocreate: token from the duplicate candidates; required with confirm_new.
human_requestedNocreate: true, set only after the human explicitly requested this Open Item.
continuity_tokenNoOptional host conversation id. Resolves the active session and pins this call's authorization, org and project to it.
expected_revisionNoOptional concurrency revision.

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: create is human-gated, duplicate-checked, and produces a decision-backed Open Item. However, it says nothing about the consequences of the lifecycle writes (whether complete/reopen are reversible, what happens on a contested claim, how expected_revision conflicts surface), leaving the mutation profile largely undisclosed.

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 with the read/create/lifecycle split and the alias mapping, and every clause is functional. The opening ontology sentence ('Every Open Item is a Decision...') is conceptual framing that costs space without changing how the tool is called.

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?

For a 22-parameter, 13-action tool with no annotations and no output schema, the description covers the create path and aliases but leaves seven lifecycle verbs semantically undefined and says nothing about return shape or error behavior. An agent can pick list/get/create confidently but must guess at the rest.

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 95%, so nearly every parameter is already documented in the schema, and the description adds only the human_requested=true requirement for create. It does not explain the interplay between confirm_new and candidate_token or how session_id/continuity_token affect authorization, so it adds little beyond the structured fields.

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 names the resource (Decisions and Open Items) and partitions the action set into reads (list/get), a gated create, and lifecycle verbs, which lets an agent distinguish the modes. It stops short of saying what each lifecycle verb (claim, assign, start, park, complete, reopen, release) actually does, so the purpose of the majority of the enum is only loosely conveyed.

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 a strong, explicit precondition for create: only on an explicit human request, human_requested=true, with duplicate checking. It also resolves the alias ambiguity (pick_up/put_down/resolved map to start/park/complete), which is real routing guidance. It offers no guidance on when to use this tool versus siblings like nasc_triage or nasc_search, and no when-not conditions.

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