Skip to main content
Glama

NASC: Networked AI Session Continuity

nasc_search

Hybrid keyword and vector search over session digests, decisions, work logs, chat chunks, wiki nodes (stubs opened by the wiki tool), and docs. With rerank, fused_top is the ranked answer with long fields previewed (_preview:true) and per-corpus rows are id, title and score stubs; get returns one record whole. If retrieval.status is partial, results contains completed sections only and coverage identifies what finished; a timeout leaves other sections inconclusive. No search continues in the background, and the response's notice and follow_up state any bounded follow-up.

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_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
getNoFetches one record whole by a hit's kind and id, with no query.
whoNoOperator whose session or last-worked project scopes a search with no project. Defaults to RJ, so another operator who omits it gets RJ's scope.
fullNoUntrimmed bodies and full per-corpus rows. Default false.
brainNoOptional org to search; it never grants access. Under enforced org scope, a value other than the call's authorized org fails the search.
queryNoNatural language query.
corpusNoDefault 'all'.
rerankNoCross-encoder rerank into fused_top. Default true.
projectNoProject slug.
session_idNoOptional session id from nasc_start. Pins this call's authorization, org and project to that session.
match_countNoMax results per corpus (1-50). Default 10.
memory_typesNoDecision memory types to include. Applies only to decision results.
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

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses that rerank produces a fused_top ranked answer with previewed long fields and per-corpus id/title/score stubs, that partial retrieval.status means only completed sections are present with coverage identifying what finished, and that a timeout leaves other sections inconclusive. It also states explicitly that no search continues in the background and that notice and follow_up carry any bounded follow-up. It does not state the read-only nature or rate/permission behavior beyond what the schema covers.

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?

Purpose is front-loaded in the first sentence and the remaining sentences each add a distinct behavioral fact (rerank output shape, partial/timeout semantics, no background work, follow-up signaling). The prose is dense and a few clauses are packed, but there is no filler or repetition. A brief structural break would improve scannability.

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 12-parameter tool with no annotations and no output schema, the description compensates well by explaining the return shape (fused_top, previews, per-corpus stubs), partial-result semantics, and follow-up signaling. Parameter-level details such as the who default and session pinning live in the schema, so the split of labor is sensible. The main gap is that the response envelope around notice/coverage is described conceptually rather than concretely.

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 100%, so every parameter including the nested get object is already documented in the schema, which sets the baseline at 3. The description adds output-shape meaning for rerank and get ('returns one record whole') but does not add syntax, defaults, or interaction rules for query, project, brain, or continuity_token beyond the schema. It largely reinforces rather than extends the parameter definitions.

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 first clause names a specific mechanism (hybrid keyword and vector search) and enumerates the corpora searched: session digests, decisions, work logs, chat chunks, wiki nodes, and docs. An agent can tell this is the broad cross-corpus search tool rather than a corpus-specific sibling. It stops short of naming which sibling to use for a single-corpus lookup, so it is clear but not fully differentiated.

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 implies usage through behavioral notes (use get to pull one record whole; rerank controls whether fused_top is the ranked answer) but never states when to prefer this over nasc_decisions, nasc_docs, or nasc_wiki for a scoped lookup. There are no explicit exclusions or prerequisites in the description itself. Guidance is inferable rather than stated.

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