Skip to main content
Glama

NASC: Networked AI Session Continuity

nasc_mailbox_pull

Scribe-lane batched pull for one machine: the credential's own live sessions there, the notifications addressed to them, and the live path-claims spanning every project those sessions touch. Restricted to the transcript-ingester capture credential; an interactive caller without it is refused.

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": {
      "machine": "<machine>"
    },
    "name": "nasc_mailbox_pull"
  }
}

Input Schema

NameRequiredDescriptionDefault
machineYesThis machine's hostname, matched case-insensitively.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full disclosure burden and does substantial work: it discloses the auth model (credential-scoped), the refusal behavior for ineligible callers, and that it is a batch read whose claims span all projects touched by those sessions. It stops short of describing result ordering, volume limits, or what an empty/refused response looks like, but the key behavioral traits are present.

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?

Two sentences, no filler, and the payload composition is front-loaded before the access restriction. Dense terminology costs some readability and the colon-heavy clause listing three items is demanding, but nothing is redundant.

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 one-parameter tool with no output schema, the description must convey what comes back, and it enumerates all three returned buckets plus the eligibility rule. The remaining gaps — result shape, volume, and behavior when a session has no notifications — are minor but real.

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?

There is a single parameter with 100% schema description coverage, so the schema already explains that 'machine' is a hostname matched case-insensitively. The description only reinforces the one-machine scoping ('for one machine') without adding format or edge-case guidance. Baseline 3 is appropriate when the schema does the explanatory 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?

The description names a specific verb ('batched pull') and enumerates the exact resources returned: the credential's live sessions on one machine, the notifications addressed to them, and live path-claims across every project those sessions touch. That enumeration is what distinguishes it from single-purpose siblings like nasc_live or nasc_notify. The heavy domain jargon ('Scribe-lane', 'path-claims') keeps a non-initiated agent from fully grasping the payload, which holds it back from a 5.

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?

It states a real precondition clearly — restricted to the transcript-ingester capture credential, and an interactive caller without it is refused — so an agent can determine up front whether it is eligible. 'Batched pull' implies the use case (fetching sessions, notifications, and claims together in one call), but no alternative tool is named for callers who lack the credential or who need only one of the three buckets.

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