Skip to main content
Glama

Quickbooks

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

A5/5.0
Behavior5/5

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

Beyond annotations (readOnlyHint, idempotentHint), the description adds rich behavioral context: embedding model (BGE-base-en), search technique (cosine over 500-char overlapping windows), character limit (200K) with truncation flag, and output format (passages with offsets and 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?

Three well-structured sentences with bold emphasis on key terms. Front-loaded with the core action, followed by use cases, usage advice, technical details, and constraints. Every sentence contributes meaning.

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?

Despite no output schema, the description fully explains what is returned (top-N passages with character offsets and similarity scores) and covers the input constraints (200K char limit). All essential information is present for correct invocation.

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

Parameters5/5

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

Schema coverage is 100% with descriptions. The description reinforces each parameter's meaning, provides concrete examples for 'query', and clarifies the default and range for 'limit'. Adds value 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' with specific examples (SEC 10-K, article, long tool result). It distinguishes from siblings like ask_pipeworx_grounded by specifying that search_within operates on already-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?

Explicitly tells when to use: 'when the record is too big to cram into the prompt' and explains benefits (saves context, returns relevant passages with offsets for verification). Mentions pairing with ask_pipeworx_grounded, providing clear guidance on workflow.

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

All Quickbooks 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

A3.5/5.0
Disambiguation2/5

Several tools are near-duplicates (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded), and there are overlapping clusters among the polymarket_* tools, research tools (deep_research, entity_profile, compare_entities, recent_changes), and AI-visibility tools (ai_visibility_check vs scan_competitor_ai_presence). The detailed descriptions help, but an agent selecting among these could easily pick the wrong one.

Naming Consistency2/5

Snake_case is used consistently, but the naming pattern is otherwise mixed: some tools are verb_noun (validate_claim, suggest_questions), some are bare nouns (entity_profile, polymarket_edges), some are verbs without objects (remember, forget, ask_pipeworx), and only the five QuickBooks tools share a qb_ prefix. This creates multiple naming ecosystems with no unified convention.

Tool Count2/5

At 36 tools, this is well above the 25+ threshold for 'too many'. More importantly, the server is named Quickbooks but only 5 tools are accounting-related; the other 31 are unrelated Pipeworx data, prediction-market, memory, and meta tools, making the count both excessive and off-purpose.

Completeness2/5

For the QuickBooks domain named by the server, the surface is read-only: get customer, get invoice, list accounts, list invoices, and generic query. There are no create, update, delete, payment, bill, deposit, or report operations, which is a significant gap. For the broader Pipeworx data domain it is fairly complete, but that domain is not what the server name promises.

Resources