qb_queryExecute a QuickBooks SQL-like query (QBO query language) against any entity type — Customer, Invoice, Account, etc. Example: "SELECT * FROM Customer MAXRESULTS 10". Returns raw QuickBooks API response with matching records.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | QuickBooks SQL-like query string (e.g., "SELECT * FROM Customer MAXRESULTS 10") |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "oneOf": [
+ {
+ "properties": {
+ "error": {
+ "description": "Error code if connection not configured",
+ "type": "string"
+ },
+ "message": {
+ "description": "Error message with setup instructions",
+ "type": "string"
+ }
+ },
+ "required": [
+ "error",
+ "message"
+ ],
+ "type": "object"
+ },
+ {
+ "properties": {
+ "QueryResponse": {
+ "description": "Array of query results matching the QuickBooks query",
+ "items": {
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "type": "object"
+ }
+ ],
+ "type": "object"
+}Input schema / examplesAdded value: +[
+ {
+ "query": "SELECT * FROM Customer MAXRESULTS 10"
+ },
+ {
+ "query": "SELECT * FROM Invoice WHERE DocNumber = '1001' AND TxnDate >= '2024-01-01'"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already state readOnlyHint, idempotentHint, destructiveHint. Description adds that it returns raw API response and uses QBO query language, but doesn't elaborate on potential limits, pagination, or error behavior. Adequate but minimal added value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with essential information front-loaded. Example included inline. No redundant words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple one-parameter tool, rich annotations, and presence of output schema (not shown but signaled), the description sufficiently covers purpose, usage, and behavior. No gaps identified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of the single parameter with a description. Description adds value by providing examples of valid queries and explaining the query syntax, which goes beyond the schema's description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool executes a QuickBooks SQL-like query against any entity type, with an example. Distinguishes from sibling tools like qb_get_customer and qb_list_accounts which are opinionated retrieval tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies general use for querying any entity, but doesn't explicitly contrast with specific getter/list tools or provide guidance on when not to use it. Could mention that for single records the dedicated getter tools may be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
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.
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.
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.
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.