Skip to main content
Glama

NS Pros MCP Gateway

ntsb-investigations__search_within

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt, search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "Apple Inc. reported fiscal 2023 revenue of $383.285 billion, driven by strong iPhone and Services growth. Net income was $96.995 billion. The company faced supply-chain risk in China during the quarter.",
      "query": "supply-chain risk"
    },
    "name": "ntsb-investigations__search_within"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe document text to search inside (max ~200K chars).
limitNoMax passages to return (1-20, default 5).
queryYesNatural-language query, what passages do you want? E.g. "supply-chain risk", "fiscal year 2024 revenue", "drug interactions with warfarin".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
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 disclose the return shape (top-N passages, character offsets, similarity scores) and the context-saving rationale, plus the verification affordance that offsets enable. It stops short of stating cost, rate limits, or what happens when the query matches nothing, so it is informative but not complete.

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?

The opening is well front-loaded, but the second half is a comma-spliced run-on ('Use when the record is too big..., search_within saves context, returns only the passages..., and every passage carries an offset') that mixes several claims into one unpunctuated clause. The text also terminates mid-sentence ('fetch with the gateway, ground'), leaving a dangling, wasted fragment.

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 three-parameter tool with no output schema and no annotations, the description supplies the critical missing pieces: what comes back, in what form, and why the offsets matter. Only the truncated trailing sentence and the absence of failure/empty-result behavior keep it from being fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns above that by clarifying what 'text' actually is ('a SEC 10-K body, an article, a long tool result') and by framing 'query' as a natural-language passage request while noting output is 'top-N' (mapping to limit). It adds practical meaning without restating the schema verbatim.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Semantic search INSIDE a fetched record') and immediately clarifies the input pattern: text you already pulled plus a natural-language query, returning top-N passages with offsets and scores. This distinguishes it from corpus-level siblings like ntsb_search_investigations, since it operates on text the agent already has rather than a remote index.

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 an explicit selection condition: 'Use when the record is too big to cram into the prompt,' which is a real, actionable trigger. It also names a companion (ask_pipeworx_grounded) for the fetch-then-ground workflow, though the sentence is cut off before the guidance is finished and no when-not case is 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.