Skip to main content
Glama

Visualcrossing

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. Added

TDQS

A4.5/5.0
Behavior5/5

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

The description adds substantial behavioral context beyond annotations: it discloses the embedding model (BGE-base-en), similarity metric (cosine), windowing (500-char overlapping windows), character limit (200K chars with truncation and flagging), and return format (passages with offsets and scores). This aligns with the annotations (readOnlyHint, idempotentHint) and provides no contradictions.

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?

The description is a single well-crafted paragraph that front-loads the core purpose. Every sentence provides useful information (use case, pairing, technical details, limitations). It could be more structurally organized (e.g., bullet points) but remains concise and readable without redundant content.

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?

Despite lacking an output schema, the description explains the return format (top-N passages, character offsets, similarity scores) and technical constraints (embedding model, windowing, character limit). This is sufficient for an agent to understand what to expect and how to use the results.

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 baseline is 3. The description adds value by clarifying 'text' as document text with max chars, 'query' as natural-language query with examples, and 'limit' with default and range. This extra context improves semantic understanding beyond the schema.

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 clearly states 'Semantic search INSIDE a fetched record' and gives concrete examples like SEC 10-K body and article. It distinguishes from the sibling tool 'ask_pipeworx_grounded' by explaining how they pair together. The verb 'search' and resource 'record' are specific and unambiguous.

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?

The description explicitly advises using this tool when the record is too large for the prompt, explaining it saves context and returns only relevant passages. It references the sibling tool 'ask_pipeworx_grounded' for grounding over passages. However, it does not explicitly state when NOT to use this tool, though the context implies it.

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

All Visualcrossing 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

A4.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose. Even tools with overlapping domains (e.g., ask_pipeworx and deep_research) are differentiated by use case: single lookups vs multi-faceted research. Weather, Polymarket, memory, and subscription tools are completely separate, and descriptions clarify any potential confusion.

Naming Consistency4/5

Tool names mostly follow a verb_noun pattern, but some are single verbs (forget, recall) or noun_noun (entity_profile, weather_timeline). The mix is noticeable but still predictable and readable, with consistent snake_case formatting throughout.

Tool Count4/5

With 34 tools, the server is large but each tool serves a specific function within the broad data-access domain. The count is justified given the wide range of domains (weather, company data, prediction markets, memory, subscriptions, etc.), though it is on the higher end for typical MCP servers.

Completeness4/5

The tool surface covers a wide range of operations: data retrieval, comparison, fact-checking, weather, prediction markets, memory, subscriptions, and meta-tools. There are no obvious gaps for the intended use of a unified data gateway, though some niche data sources might not be directly addressed.

Resources