Skip to main content
Glama

Data Issy

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

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnly, openWorld, idempotent, non-destructive. The description adds substantial behavioral details: BGE-base-en embeddings, cosine similarity over 500-char overlapping windows, 200K char cap with truncation flag, and return of offsets for verification. This far exceeds what annotations provide.

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?

Three sentences that are front-loaded with purpose, then a clear usage guideline, and finally the technical behavior. No fluff; every clause adds distinct value.

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 the complexity of semantic search, the description covers input constraints (200K chars), embedding model, windowing, scoring, output format (passages with offsets), and a pairing suggestion. No output schema exists, but the description adequately describes return structure. All important aspects are addressed.

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 covers all parameters with descriptions (100% coverage). Description reinforces the query parameter as natural-language with examples and notes that passages include offsets for verification, adding context beyond the schema's mechanical definition. Limit defaults are already in schema, but the assistant gains value from the examples and usage framing.

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 explicitly states 'Semantic search INSIDE a fetched record' with concrete examples (SEC 10-K, article) and clearly distinguishes from sibling tools like ask_pipeworx_grounded by specifying that search_within operates on previously fetched text.

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?

Provides explicit when-to-use: 'Use when the record is too big to cram into the prompt' and pairs with ask_pipeworx_grounded, which frames when not to use this tool (grounding over passages vs. whole document). No exclusions are needed beyond this.

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

All Data Issy 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
Disambiguation3/5

The toolset is mostly organized by clear subdomains, but there are multiple overlapping entry points: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all answer research questions and the beta version is currently identical to the stable router. Detailed descriptions reduce confusion, but an agent could still reasonably pick the wrong one for a given task. The entity, memory, and subscription tools are more clearly separated.

Naming Consistency3/5

Names are consistently lower_snake_case and readable, but the set mixes verb-led names (compare_entities, resolve_entity, validate_claim) with noun-led names (entity_profile, polymarket_edges, pipeworx_trending) and some odd pairings like ai_visibility_check vs scan_competitor_ai_presence. No chaotic camelCase or inconsistent separators, but the convention is not uniform enough for a strong score.

Tool Count2/5

34 tools is past the 25+ threshold and the surface spans many unrelated domains: structured data lookup, prediction markets, AI visibility marketing, city open data, npm dependency checking, llms.txt generation, memory, and subscriptions. Each tool may be individually useful, but the collection feels like a platform dump rather than a tightly scoped server. A more focused server would split off prediction markets, AI visibility, and utility tools.

Completeness4/5

The main data-research workflow is well covered: discovery, routing, grounded answering, deep research, entity resolution, profiles, comparisons, recent changes, claim validation, and search-within-results are all present. Prediction-market analysis, memory, and subscription lifecycles also have no major dead ends. Minor gaps exist, such as no write/update path for open data and no subscription option for AI-visibility monitoring, but these are not central to the apparent core purpose.

Resources