Skip to main content
Glama

Data Va

by io.github.pipeworx-io

Search Within a Source

search_within
Read-onlyIdempotent

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 over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

Input Schema

TableJSON 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. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly/openWorld/idempotent hints, so the bar is lower. The description adds substantial behavioral detail: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, 200K char cap with truncation flagging, and output containing offsets and similarity scores. No contradictions with annotations.

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

Conciseness5/5

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

Four sentences, front-loaded with purpose, then usage, then technical details. Every sentence earns its place — no filler, no repetition of schema content. The structure flows logically from what → when → how.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description compensates by explaining the return format (top-N passages, character offsets, similarity scores). It also covers edge conditions (200K truncation) and pairing with other tools. For a search tool with 3 simple params, this is complete.

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 baseline is 3. All parameters (text, query, limit) are already well-described in the schema with examples. The description reinforces that 'text' is the already-fetched record and that query is natural-language, but adds no new semantic detail beyond what the schema provides.

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?

The description opens with 'Semantic search INSIDE a fetched record,' a specific verb+resource pair. It immediately distinguishes itself from siblings like ask_pipeworx or query by emphasizing this operates on already-fetched text, and it pairs with ask_pipeworx_grounded, clarifying its niche.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'Use when the record is too big to cram into the prompt.' It also describes the integration pattern with ask_pipeworx_grounded, giving a clear workflow. This provides both a use case and an alternative/companion tool, exceeding the minimum guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Data Va toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation2/5

Several tool clusters are near-duplicates or easy to confuse: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are nearly identical (beta currently matches stable exactly), while polymarket_edges, polymarket_arbitrage, and bet_research all scan prediction-market opportunities with overlapping outputs. entity_profile/compare_entities/recent_changes and ai_visibility_check/scan_competitor_ai_presence add further redundancy. Despite detailed descriptions, the boundaries require careful reading, so an agent is likely to misselect.

Naming Consistency3/5

All names are snake_case and readable, with useful prefixes like ask_, polymarket_, pipeworx_, and scan_. However, conventions are mixed: verb_noun (ask_pipeworx, list_subscriptions, resolve_entity) coexists with bare nouns (datasets, metadata, query) and noun-first compounds (entity_profile, bet_research, deep_research). There is no single predictable pattern.

Tool Count2/5

34 tools is above the 25-tool threshold, and the set spans multiple unrelated domains such as data routing, prediction markets, memory, subscriptions, Virginia Open Data, AI visibility, and npm dependency checks. Several tools are effectively wrappers or near-overlaps that could be consolidated, e.g., ai_visibility_check vs scan_competitor_ai_presence and polymarket_edges vs polymarket_arbitrage. The surface feels bloated for a single server.

Completeness4/5

Within its main sub-domains the set is solid: memory has remember/recall/forget, subscriptions have subscribe/unsubscribe/list/recent_alerts, research has resolve_entity/compare_entities/entity_profile/recent_changes/validate_claim, and Polymarket has detection/arbitrage/fill-risk/edge-tracking. Minor gaps exist — no tool to fetch a raw pipeworx:// record, no write/update for Virginia Open Data, and no trade execution for prediction markets — but these do not create dead ends for a research-focused agent.

Resources