QuickBooks Online MCP Server

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v0.0.1
Disambiguation5/5
Each tool targets a distinct entity and action, with clear verb-entity patterns. There is no overlap between tools as they follow a consistent structure per entity (create, get, search, update, delete), making it easy for an agent to select the correct tool.
Naming Consistency3/5
The naming uses a mix of underscore and hyphen delimiters (e.g., create_account vs create-bill) and some verbs are inconsistent (e.g., get_account vs read_invoice). While still readable, the lack of a uniform pattern may cause confusion for an agent.
Tool Count2/5
With 140 tools, the server has an excessive number for typical MCP usage. Although the breadth of QuickBooks Online justifies many operations, the sheer volume makes the tool surface overwhelming and difficult for an agent to navigate efficiently.
Completeness4/5
The tool set covers nearly all main entities (accounts, customers, vendors, invoices, etc.) with full CRUD operations plus financial reports. Minor gaps exist, such as missing delete for a few entity types (e.g., account, class) and some reports not having update capability, but overall it is highly comprehensive.
Average 2.9/5 across 140 of 140 tools scored. Lowest: 2.2/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 14 commits in the last 12 weeks
- No stable releases found
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI status not available
This repository is licensed under Apache 2.0.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description provides no behavioral details beyond the basic purpose. It does not indicate that the operation is read-only, whether authentication is required, or if results are paginated. With no annotations, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
While very concise, the description is under-specified and lacks crucial details about functionality, usage context, and output. It does not earn its place by providing value beyond the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is a search with filtering parameters and no output schema, but the description does not explain what is returned, pagination behavior, or default limit. It is incomplete for an agent to use effectively.
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?
The input schema already describes all parameters (vendor_ref, date range, limit, company), so the description adds no additional meaning. Schema coverage is high, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Search' and the resource 'purchase orders', but it does not differentiate from sibling search tools like search_purchases or search_bills, which operate on similar resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. There is no mention of filtering capabilities, prerequisites, or situations where other tools (e.g., get_purchase_order) would be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It fails to disclose behavioral traits such as idempotency, authentication requirements, rate limits, or side effects. The agent cannot infer safety or behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks necessary detail. It is appropriately front-loaded, but the absence of structured information reduces its effectiveness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (7 nested parameters, no output schema, no annotations), the description is severely incomplete. The agent cannot understand how to construct a meaningful search or interpret results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (only the 'company' parameter has a description). The description adds no parameter-level information, leaving the agent uncertain about how to use 'criteria', 'limit', 'offset', etc.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the purpose: 'Search purchases in QuickBooks Online that match given criteria.' The verb and resource are explicit. However, it does not distinguish itself from numerous sibling search tools, making it generic.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like search_bills, search_invoices, etc. No mention of prerequisites or context, leaving the agent without sufficient direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose any behavioral traits such as read-only nature, pagination, or data scope. With no annotations, the description should compensate but fails to do so.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks necessary details. It could be improved by including behavioral or usage information without significant bloat.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a search tool with no output schema and sparse annotations, the description is insufficient. It omits crucial context like result format, pagination, and filtering behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning to the parameters beyond what the input schema provides. With 50% schema coverage, the description does little to clarify the purpose of the 'params' object or 'company' field.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose3/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the verb 'search' and resource 'transfers' in QuickBooks Online, but does not define what constitutes a transfer or differentiate it from other search tools among siblings. It is clear but vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like get_transfer or other search tools. The description lacks context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It only states the action ('Create') without disclosing side effects, idempotency, or required permissions, leaving significant gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but severely under-specified. It does not earn its place as it fails to provide essential information beyond the name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, no annotations, and a complex nested parameter left undefined, the description is wholly incomplete. An agent cannot determine how to construct the billPaymen object or interpret the result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has two parameters, and only 'company' has a description (50% coverage). The main parameter 'billPayment' is an opaque object with no description in either schema or tool description. The tool description adds no parameter meaning beyond 'Create a bill payment'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Create') and resource ('bill payment in QuickBooks Online'), clearly indicating the action and context. However, it does not distinguish from sibling tools like 'create_payment' or 'create-bill', which could cause confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., when to use create_payment for other payment types). No prerequisites or conditions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It only states a generic creation action, omitting critical details like idempotency, side effects (e.g., does it affect inventory?), required permissions, or default behaviors (e.g., date handling). This is insufficient for an agent to understand the tool's operational consequences.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at one sentence, which is efficient but sacrifices essential information. It is front-loaded with the main action, but brevity here undermines clarity and completeness, making it minimally acceptable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested parameters, no output schema, no annotations), the description is severely incomplete. It fails to explain the overall workflow, success/error expectations, required vs optional fields, or any post-condition behavior. An agent would lack the context to use this tool reliably.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low (50% from context, only the 'company' parameter has a description). The description does not explain any parameters, leaving the agent to infer meanings from parameter names alone. For nested objects like 'line_items,' the schema provides types and constraints but no semantic context (e.g., what 'item_ref' represents), and the description adds nothing.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the verb 'Create' and the resource 'invoice in QuickBooks Online,' which clearly identifies the tool's primary function. However, it does not differentiate from sibling tools like 'create_sales_receipt' or 'create_credit_memo,' which could lead to confusion for an agent selecting among similar creation tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as when to create an invoice versus a sales receipt or credit memo. No prerequisites, exclusions, or contextual hints are given, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It does not disclose any behavioral traits such as mutability, required permissions, side effects, or success/failure behavior. For a creation tool, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise and front-loaded. However, it sacrifices necessary detail, making it insufficiently informative. It earns its place but does not maximize utility.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has a nested parameter object with six properties, no output schema, and no annotations, the description is severely lacking. It fails to explain what an item is, how parameters relate to business logic, or what the return value will be. This is incomplete for agents.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only the 'company' field has a description). The tool description adds no clarification for the inner param properties (name, type, income_account_ref, etc.). Users must infer meaning from parameter names alone, which is insufficient for correct invocation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Create' and the resource 'item in QuickBooks Online', making the tool's purpose immediately understandable. However, it does not explicitly distinguish from other create tools, though the specific term 'item' differentiates it from siblings like create_customer or create_invoice.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., update_item for existing items, or other create_* tools for different entities). The description lacks context about prerequisites, error conditions, or recommended use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description gives no behavioral details such as required permissions, side effects, or what happens upon creation. The description is minimal and does not compensate for the lack of annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words, but it is too brief to be fully informative. It earns its place but lacks essential details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of creating a purchase with a nested object parameter and no output schema, the description is severely inadequate. It does not explain the purchase object, required fields, or what the agent should expect as a response, leaving significant gaps in usability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50%, with only the 'company' parameter having a description. The 'params' object, which contains the main purchase data, is completely undocumented. The description adds no meaning beyond what the schema provides, leaving the agent without guidance on the structure or required fields of 'purchase'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool creates a purchase in QuickBooks Online. It is a specific verb+resource, and the tool name 'create_purchase' distinguishes it from sibling tools like 'create_bill' or 'create_purchase_order', though it does not elaborate on the differences.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives such as create_bill or create_purchase_order. The description lacks context about typical use cases or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits such as pagination, read-only nature, rate limits, or authentication needs. It adds no transparency beyond the tool name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, but it is too concise and omits critical details. It sacrifices informativeness for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a complex schema with nested objects and multiple parameters, no output schema, and no annotations. The description fails to cover return values, filtering details, pagination behavior, or any other contextual information needed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50%, but the description adds no meaning to any parameter. The 'criteria' array, pagination fields, and other properties are left entirely unexplained, which is insufficient for correct invocation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches employees matching criteria, which is a specific verb and resource. It distinguishes from other employee tools like get_employee, but does not differentiate among other search tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like get_employee or other search tools. No prerequisites or exclusion criteria mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for transparency. It only states 'update,' indicating mutation, but does not disclose behavioral traits such as idempotency, required permissions, error scenarios, or whether the tool returns the updated estimate. Minimal information leaves agents uncertain about side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence but is under-informative. It lacks front-loading of key details and does not structure information beyond the basic action-object pair. Conciseness here sacrifices utility.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of updating an accounting estimate (nested object, multiple possible fields) and the absence of output schema or annotations, the description is severely incomplete. It does not address return values, error handling, or typical scenarios, making it insufficient for reliable agent invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only 'company' has a description). The critical 'params.estimate' object has no description or type definition, and the tool description adds no meaning. The agent has no insight into the structure or required fields of the estimate data.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('update') and the resource ('estimate in QuickBooks Online'). It distinguishes itself from sibling tools like create_estimate and delete_estimate by implying modification of an existing estimate. However, it lacks details on scoping or specific fields that can be updated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs. alternatives like create_estimate or other update tools. There is no mention of prerequisites (e.g., estimate must exist), context of use, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description is extremely minimal and does not disclose any behavioral traits beyond the bare action. No annotations are present, so the description must convey safety, side effects, or required permissions, but it fails to do so. This could mislead an agent into believing it's a benign deletion without consequences.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (one sentence), which is concise but lacks necessary detail. It is front-loaded, but the brevity detracts from its usefulness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a delete operation with nested parameters and no output schema, the description is incomplete. It fails to explain return values, side effects, or required context such as company identification.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers 50% of parameters (only 'company' has a description). The description does not add any meaning for the 'idOrEntity' parameter within 'params', leaving its semantics unclear. With low schema coverage, the description should explain the parameter's purpose but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'delete' and the resource 'transfer', specifying the domain 'QuickBooks Online'. This provides a clear purpose, though it does not distinguish it from other delete tools in the sibling list.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, conditions, or when not to use it, which is problematic given the many sibling delete operations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only mentions 'search' implying read-only, but omits details like pagination, ordering, default behavior, or error handling. The schema hints at pagination (limit, offset, fetchAll) but these are not described in text.
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 very concise with a single sentence. However, it sacrifices necessary detail, particularly for parameters and behaviors. Still, it is well-front-loaded and contains no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested params, pagination support, no output schema), the description is far too minimal. It fails to explain return values, pagination behavior, or criteria structure, leaving the agent with inadequate context to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low (50% only on the top-level company parameter). The description does not explain the 'criteria' parameter format (array of what?) nor any other params (asc, desc, limit, etc.). It adds no meaningful semantics beyond the schema structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool searches journal entries in QuickBooks Online matching given criteria. It uses a specific verb+resource pattern and distinguishes from other search entities by name, but doesn't elaborate on what criteria are supported beyond the generic phrase.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., search for other entities). There are no explicit when-to-use, when-not-to-use, or alternative suggestions, leaving the agent to infer from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states 'Update', implying mutation, but omits side effects, permissions, idempotency, or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (6 words), which achieves conciseness but sacrifices completeness. It is front-loaded but lacks necessary detail for effective selection and usage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations, output schema, and detailed parameter guidance, the description is insufficient for an agent to confidently use this tool. It omits return value information and usage flow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (based on context), but the tool description provides no parameter information beyond what the schema already conveys. It does not clarify the role or constraints of parameters like sync_token or private_note.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Update') and resource ('a deposit'), clearly distinguishing it from sibling create and delete tools. However, it does not elaborate on the scope or unique aspects beyond the name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., create_deposit, delete_deposit). No mention of prerequisites or scenarios, leaving the agent to infer from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It fails to mention whether the update is partial or full, required permissions, destructiveness, or return behavior. Purely stating 'Update' is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but overly terse. Given the complexity of the tool (nested employee object, many sibling tools), it sacrifices necessary detail for brevity. It is under-specified rather than efficiently concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a nested parameter, no output schema, no annotations, and a large set of sibling tools. The description fails to explain how to structure the employee update, what the response looks like, or any constraints. It is severely incomplete for effective invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only 'company' parameter is documented). The description adds no parameter meanings beyond the schema. The nested 'employee' object lacks any property descriptions, and the description does not clarify what fields can be updated.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update') and resource ('an employee in QuickBooks Online'). However, it does not distinguish this tool from other update tools (e.g., update_account, update_customer) beyond the resource name. While the purpose is clear, it lacks specificity about scope or unique aspects.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like create_employee or delete_employee. There are no prerequisites, conditions, or examples for invoking this tool. The description offers no usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only states 'Update a purchase' without disclosing key behavioral traits like whether the update is partial or full replacement, what happens if the purchase does not exist, or any authentication requirements. This is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (one sentence) but fails to convey essential information. It does not earn its place as it only restates the tool name. A concise description should be front-loaded with key details, but here it is under-specified.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a nested required parameter ('purchase') with no schema description, no output schema, and no annotations, the description is completely inadequate. It fails to explain the return value, error conditions, or how to structure the update body, making it nearly unusable for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers 50% of parameters with descriptions (only 'company' has a description). The description adds no additional meaning beyond what is in the schema; it does not explain the structure or required fields of the 'purchase' object inside 'params'. The agent is left guessing.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'a purchase in QuickBooks Online', which is specific and tells the agent what the tool does. However, it does not distinguish from sibling tools like 'update_purchase_order' or 'update_bill', but the resource name is distinct enough to avoid confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as when to create a purchase instead. There is no mention of prerequisites or exclusions, leaving the agent without context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It only restates the tool's name without disclosing any behavioral traits such as concurrency control via sync_token, permission requirements, or effects of updates.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise but lacks necessary detail. One sentence may be too minimal for users to understand the tool's purpose and usage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of updates (concurrency, partial updates) and no output schema, the description is entirely inadequate. It does not explain return values, allowed modifications, or error handling.
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?
The input schema already provides clear descriptions for all parameters. The description adds no additional meaning beyond the schema, but with full schema coverage, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (update) and resource (transfer) in QuickBooks Online. It is not a tautology and is specific enough to distinguish from other update tools for different resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use update versus create or delete transfers. No criteria for updates, prerequisites, or context for usage relative to other transfer tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description offers no information about behavioral traits like concurrency control, error conditions, or side effects. It merely restates the tool name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one sentence), but it sacrifices useful detail. It earns its place but could be more informative without adding much length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and the tool's mutation nature, the description is severely incomplete. It fails to explain behavior, return value, or parameter details beyond what the schema provides.
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?
The input schema already provides descriptions for all parameters (100% coverage), so the description adds no additional meaning. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update') and the resource ('a vendor credit'), but does not distinguish it from sibling tools like create_vendor_credit or delete_vendor_credit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs alternatives, nor any prerequisites for use such as needing the sync_token.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits. It only states the action without mentioning permissions, side effects, or response behavior. This leaves significant unknowns.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, achieving conciseness. However, it is too short to convey necessary information, making it underinformative rather than concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a journal entry tool with no annotations, no output schema, and many similar siblings, the description is severely incomplete. It omits essential details like required fields, structure of the journal entry (debits/credits), and prerequisites.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaning only to the 'company' parameter (explaining it's a realm ID). The 'params' object remains completely undocumented, despite being required and containing the journal entry data. Schema coverage is 50% but the description does not compensate for the gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Create a journal entry in QuickBooks Online', clearly identifying the action and resource. However, it does not distinguish journal entries from other financial documents like invoices or purchases, which are among the sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., create_invoice, create_purchase). The description lacks any usage context or constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavior. It indicates a read operation (search) but fails to mention side effects, rate limits, authentication needs, or pagination behavior. The reference to 'node-quickbooks findItems' adds implementation detail but not behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one sentence, concise but lacking essential details. The parenthetical about 'node-quickbooks findItems' is potentially confusing and adds no value for the agent. It achieves conciseness but at the cost of completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, annotations, and only 50% schema coverage, the description is severely incomplete. It does not explain the criteria format, search behavior, result structure, or handling of multiple results. For a search tool with complex parameters, this is insufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds little beyond the schema: 'using criteria' echoes the criteria property without explaining its structure or allowed values. The company parameter is already described in the schema. Schema coverage is 50%, but the description does not compensate for the undocumented criteria.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it searches items in QuickBooks Online using criteria, distinguishing it from other search tools (e.g., search_accounts, search_customers). The verb 'search' and resource 'items' are specific, but the description could better clarify what types of items are included.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., read_item for a single item, create_item for adding items). Does not mention prerequisites, exclusions, or context for using criteria-based search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description does not disclose any behavioral traits such as permissions required, side effects, or error conditions. Only that it creates a bill.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and to the point, but it sacrifices critical information for brevity given the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and a complex input schema, the description lacks information about return values, required fields beyond schema, and typical usage examples. Incomplete considering the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 50% (only 'company' has a description). The description adds no meaning about the 'params' object or its nested properties, leaving the agent to infer from schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Create' and the resource 'bill' within QuickBooks Online. However, it does not differentiate from sibling tools like 'create_invoice' or 'create_purchase_order', which also create financial documents.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., create_purchase, create_vendor_credit). No prerequisites or context for usage are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only says 'Create a customer' without mentioning idempotency, error behavior on duplicates, required permissions, or response format. This is insufficient for safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
It is very brief (one sentence), but the brevity sacrifices critical information. While front-loaded, it is too minimal to be considered well-structured for its complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested object parameter and lack of output schema, the description is incomplete. It does not explain what the customer object should contain or what the tool returns, making it hard for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (company is described, params.customer is not). The description adds no additional meaning beyond the schema, failing to explain the customer object structure or any constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (create) and resource (customer) within QuickBooks Online. It distinguishes from siblings like create_account or create_employee by specifying the resource, though it doesn't elaborate on what a customer entails.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., update_customer). The description merely states the action, with no context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, and the description gives no behavioral details (e.g., that estimates are non-posting, can be converted to invoices, or require specific permissions). The agent must assume standard creation behavior without any safety notes.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, which is concise but sacrifices content. It could benefit from a few more details without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of 20+ sibling create tools and a complex nested parameter without schema details, the description is highly incomplete. It fails to provide enough context for correct parameter construction or to differentiate from similar tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description ignores parameters entirely. The input schema shows a nested 'estimate' object with no inner definition, and the description offers no hints about its structure or required fields. Schema coverage is 50% (only 'company' has a description), leaving the most critical parameter unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Create') and resource ('estimate'), and identifies the system ('QuickBooks Online'). It is distinct from sibling create tools that target different entities, but lacks additional context about the purpose of an estimate versus other documents.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like create_invoice or create_sales_receipt. Users are left to infer the appropriate context based solely on the tool name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description provides no behavioral details beyond 'create'. With no annotations present, it fails to disclose side effects, authorization requirements, or constraints (e.g., whether duplicate vendors are allowed). The agent gains minimal insight into the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, short sentence, which is concise. However, it omits essential information about parameters, usage, and behavior, making it under-specified rather than efficiently compact.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested vendor object, optional company) and lack of output schema, the description is too sparse. It does not mention return values, error conditions, or the impact of missing fields, leaving the agent with insufficient context for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 50% parameter description coverage (only the 'company' field is described). The description adds no additional meaning for the 'vendor' object's properties, leaving many fields (e.g., CountrySubDivisionCode) without explanation. The description does not compensate for the schema's gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create') and the resource ('a vendor in QuickBooks Online'), making the tool's purpose immediately understandable. However, it does not differentiate from sibling tools like create_customer or create_account, which share the same verb and context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool over alternatives (e.g., create_customer, create_vendor_credit). There is no mention of prerequisites, typical use cases, or situations where this tool should be avoided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It only states 'Delete', implying a destructive action, but does not disclose any behavioral details like irreversibility, permission requirements, or side effects on linked records.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (one sentence, 6 words) and front-loads the action. However, it is too brief and lacks any structure or additional details that could aid understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (2 parameters, one required, no output schema, many sibling tools), the description is incomplete. It does not explain what happens after deletion, how to identify the deposit, or any return information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about parameters beyond what the input schema provides. The 'idOrEntity' parameter is not described, and its format remains unclear. Schema coverage is only 50%, and the description fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (delete), resource (deposit), and context (QuickBooks Online). It is specific and unambiguous, though it does not differentiate from sibling delete tools for other entities, but that is not necessary as the resource is named.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as other delete tools or updating the deposit. No prerequisites or conditions for deletion are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries full burden. It does not disclose if the tool is read-only, what side effects exist, or how to handle errors. For a report generation tool, information about output format or duration is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise at one sentence, but it lacks essential detail given the tool's complexity (multiple parameters, nested objects). It achieves brevity but sacrifices informativeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description should explain return values or report format, which it does not. It also fails to differentiate from similar financial report tools among the siblings.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. Schema description coverage is given as 50%, and the tool description does not compensate by explaining any parameters. The nested 'params' object and 'company' field are not elaborated upon.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Generate a Profit and Loss (Income Statement) report' which is a specific verb and resource. However, it does not explicitly differentiate from sibling tools like 'get_balance_sheet' or 'get_cash_flow', though the name implies the purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. No context is given about prerequisites, such as needing a QuickBooks connection or specifying a company.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It states 'search' implying read-only, but does not disclose behavioral traits such as rate limits, pagination behavior, or effects. The schema hints at pagination parameters, but the description ignores this.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 9 words, which is concise but lacks structure. It does not front-load critical information or break down complex aspects, making it minimally adequate.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has two parameters, a nested object, no output schema, and many siblings, the description is very incomplete. It does not explain the return format, pagination, or criteria structure, leaving significant gaps for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only the 'company' parameter has a description in the schema. The description adds 'match given criteria' but does not explain the structure of the 'criteria' array or the meaning of 'asc', 'desc', 'limit', 'offset', 'count', 'fetchAll'. With 50% schema description coverage, the description fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Search' and resource 'bill payments' in QuickBooks Online, clearly indicating what the tool does. It distinguishes from siblings by entity name, but does not further differentiate itself from other search tools, which is acceptable but not exceptional.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like search_bills or other search tools. The description only implies usage for bill payments, but does not state exclusions or provide context for choosing this tool over siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits. It only says 'search bills that match given criteria,' omitting details about pagination (limit, offset), sorting (asc, desc), fetchAll, count, and company parameter. The complex criteria structure is not explained.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks structure. It does not front-load important information like search capabilities or typical usage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complex schema (nested criteria, multiple pagination parameters) and no output schema, the description is incomplete. It does not explain return values, pagination behavior, or how to use criteria effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low (approx. 29% of top-level parameters described). The description adds no parameter semantics beyond what the schema already provides, missing explanations for limit, offset, asc, desc, fetchAll, count.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches bills in QuickBooks Online with criteria, which distinguishes it from other search tools for different entities. However, it could be more precise about the nature of the search (e.g., listing bills) rather than a generic 'search'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like get-bill for a single bill or other search tools. The description lacks context about typical use cases or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It fails to mention that the tool is read-only, returns a list of customers, or explain pagination behavior (even though the schema includes limit/offset). No discussion of performance or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise and front-loaded. However, it is under-specified, lacking important context. Conciseness at the expense of completeness reduces effectiveness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the parameters (nested objects, pagination, multiple filter forms) and the absence of annotations and output schema, the description is too brief. It does not explain the advanced filter structure, pagination default, or company targeting, leaving significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
While the schema covers 50% of parameters with descriptions (e.g., criteria and company), the tool description adds no additional meaning beyond 'match given criteria'. It does not explain the two forms of criteria (advanced vs. legacy) or the purpose of limit/offset/fetchAll, which would help an agent use parameters effectively.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Search' and the resource 'customers in QuickBooks Online', indicating what the tool does. However, it does not differentiate from sibling search tools like search_accounts or search_invoices, which follow the same pattern.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as get_customer for a single record or other search tools. The description only says 'match given criteria' without any context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility but only says 'with optional filters'. It does not disclose if the operation is read-only, whether pagination is supported, or what happens if no filters are provided. Critical behavioral traits are omitted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (one short sentence), which is efficient but lacks structure. It front-loads the key action but omits any details about parameters or return value, making it too brief.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and annotations, the description should explain what results to expect (e.g., returns a list of departments). It does not cover pagination, default behavior, or required permissions, leaving significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no value beyond the input schema; it simply mentions 'optional filters' without listing them. The schema already describes each parameter, but the description should ideally provide usage context, which it fails to do.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Search' and the resource 'departments', making the tool's purpose immediately understandable. However, it does not differentiate from sibling search tools like search_accounts or search_customers, which share similar patterns.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as get_department (for a single department) or other search tools. There is no mention of prerequisites or optimal use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fails to disclose behavioral traits like read-only nature, idempotency, or side effects. It implies a read operation but doesn't explicitly confirm safety.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence) but lacks essential content. It is appropriately sized for a simple search tool but omits important details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is incomplete. It does not explain return values, pagination, or prerequisites. Compared to sibling tools, it provides minimal contextual information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema describes parameters (txn_date_from, txn_date_to, limit, company) with basic descriptions, but the tool description adds no additional meaning. Schema coverage is 50% but the description compensates nothing.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Search for deposits in QuickBooks Online' clearly identifies the action (search) and resource (deposits) within the platform. It differentiates from siblings like get_deposit (single retrieval) and CRUD operations, though it lacks detail on the scope of results.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like get_deposit for a single deposit or other search tools. No conditions or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behaviors like all results returned, pagination, or side effects; it does not, only stating generic search capability.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise but under-specified; it could be longer to cover necessary details without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and nested parameters, the description is incomplete—missing return format, pagination, and company parameter explanation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description only says 'optional filters', adding no meaning beyond the schema's property descriptions. With 50% schema coverage, the description does not compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (search) and resource (tax codes) and mentions optional filters, but it does not differentiate from many sibling search tools with similar patterns.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like get_tax_code, nor any context for usage decisions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description lacks disclosure of behavioral traits like pagination, sorting, rate limits, or result handling. The description adds no behavioral context beyond the basic search functionality implied by the name.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, but it could include more detail without becoming verbose. It is efficient but lacks substance for a search tool with multiple parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema or annotations, the description should provide more context about return values, pagination behavior, or limitations. The current description is too minimal for a search tool with a nested parameter object.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no extra meaning beyond the input schema; it only says 'with optional filters.' The schema provides descriptions for individual parameters, so the description does not enhance understanding of their usage or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for payment terms in QuickBooks Online, specifying the resource (payment terms) and action (search). However, it does not explicitly differentiate from sibling search tools like search_customers or get_term, which retrieve specific entities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions optional filters but provides no guidance on when to use this tool versus alternatives such as get_term for retrieving a single term, or other search tools for different entities. No exclusions or context for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose behavioral traits such as whether the search is read-only, any permission requirements, rate limits, or pagination behavior. The agent is left to infer that it is a read operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks structure. It provides minimal information, fitting into the 'efficient' category, but does not organize details like usage context or parameter hints.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (6 sub-parameters, nested object) and no output schema, the description is insufficient. It does not mention pagination, default limits, or how results are returned, leaving significant gaps for an agent to use effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. With schema description coverage at 50% (only half of top-level parameters have descriptions), the description could compensate but does not. The schema itself describes sub-parameters, but the overall params object lacks description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Search for time activities in QuickBooks Online,' which clearly identifies the action (search) and resource (time activities). It distinguishes from sibling tools like get_time_activity by implying a list/query operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs alternatives such as get_time_activity (for single item) or other search tools. The description lacks context on suitable use cases or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only says 'Search', implying a read-only operation, but does not disclose if it returns a list, pagination behavior, or any side effects. Since no annotations are provided, the description carries the full burden of behavioral disclosure and fails to provide meaningful detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, making it concise. However, it is too sparse and lacks structured information (e.g., behavior, parameters). While it earns its place, it does not effectively front-load key details for an AI agent.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain what the search returns (e.g., list of vendor credits, total count). It also fails to differentiate from 'get_vendor_credit' or align with sibling search tools. The context signals (2 params, 50% coverage) highlight gaps that the description does not address.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides descriptions for 'vendor_ref' and 'limit' inside the 'params' object, but the 'params' object itself lacks a description. The tool description ('Search for vendor credits') adds no parameter meaning beyond the schema. With 50% schema coverage at top level, the description should compensate but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Search') and resource ('vendor credits in QuickBooks Online'). However, it does not differentiate from sibling tools like 'get_vendor_credit' or 'create_vendor_credit', which could confuse an AI agent about which tool to use for listing vs. retrieving a single credit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'get_vendor_credit' or other search tools. There are no exclusions, prerequisites, or context about using vendor_ref or limit parameters.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It only says 'Update', but does not explain if this is a partial or full replacement, whether it is destructive, idempotent, or what happens when the account does not exist. No mention of authentication, rate limits, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise and front-loaded, but it omits critical information. It is not overly verbose, but it sacrifices completeness for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool is a mutation with a nested patch parameter, no output schema, and no annotations, the description is incomplete. It does not explain return values, error behavior, or what fields are updatable, leaving significant gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 50% (only 'company' described). The description adds no details about 'account_id' (e.g., format, source) or 'patch' (e.g., allowed fields, structure). The agent is left to infer the patch object's expected properties without guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool updates an existing chart-of-accounts entry in Quickbooks, using a specific verb and resource. Among siblings, it is the only 'update_account' tool, so it is easily distinguishable from create, get, search, and delete tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'create_account' or other update tools. It does not mention prerequisites, such as needing an existing account ID, or when a patch is appropriate over full update.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavior. 'Update' implies mutation, but the description does not state whether permissions are required, if updates are reversible, what happens if the customer does not exist, or how errors are handled. This lack of detail leaves the agent uncertain about side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words, achieving conciseness. However, it is arguably too brief, sacrificing necessary detail. While front-loading is adequate, the sentence fails to cover important aspects, so it is not optimally structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of QuickBooks and the presence of many sibling tools, the description is insufficient. It does not explain how to identify the customer (e.g., by ID), what fields are updatable, or provide any return value expectations. With no output schema, the agent is left without a clear picture of the tool's full behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 50% description coverage (only 'company' has a description). The 'params' object is undocumented in both schema and description, leaving agents to guess its structure. The description adds no meaning beyond the schema, failing to clarify what properties the customer object should contain.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update', the resource 'existing customer', and the system 'QuickBooks Online'. It distinguishes from sibling tools like 'create_customer' and 'delete_customer' by indicating modification of an existing record. However, it does not specify which customer fields can be updated, leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as when a customer should be created or deleted instead. No prerequisites, context, or exclusion criteria are mentioned, making it difficult for an agent to decide when to invoke this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full behavioral burden but only says 'Update'. It does not disclose traits like optimistic locking via sync_token, idempotency, permission requirements, or return behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (one sentence), which is concise but under-specified. It could include essential details without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is incomplete. It omits critical context like the need to first retrieve the purchase order for sync_token, or the fact that fields like id and sync_token are required.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (top-level params object lacks description). The tool's description adds no parameter meaning beyond the schema, failing to compensate for missing descriptions of the nested object.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it updates an existing purchase order in QuickBooks Online, distinguishing it from create and delete sibling tools. However, it lacks specificity on the scope of updatable fields.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives (e.g., create_purchase_order, delete_purchase_order). The description does not mention prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description fails to disclose behavioral traits such as required permissions, error handling, or that it requires a SyncToken for optimistic locking. The description simply says 'update' without any additional context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (6 words), but this under-specification results in a lack of useful information. It is front-loaded but too brief for a tool with nested parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a complex input schema with nested objects, the description is insufficient. It does not cover key aspects like required fields (Id, SyncToken) or the purpose of optional fields.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the schema. With only 50% schema description coverage, the vendor object's many properties are undocumented, and the description does not compensate by explaining their purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Update a vendor' with a specific verb and resource. It distinguishes from 'create-vendor' and other sibling tools by implication, but does not explicitly differentiate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives (e.g., when to update vs create). No prerequisites or context are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits (e.g., permissions required, side effects like updating customer balance, or whether the credit memo can be edited later). The description is silent on what happens when the tool is invoked.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but overly brief. It lacks structure and additional sentences that could provide necessary context without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of creating a credit memo with nested line items, the description is incomplete. It does not mention required fields (customer_ref, line_items), defaults, or error conditions. No output schema is provided to explain the return value.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With schema description coverage at 50%, the description adds no extra meaning to the parameters. The tool description does not explain how to use the parameters (e.g., how line items work, format of dates). The schema provides minimal descriptions, but the tool description should compensate for the low coverage.
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?
Description clearly states the action (create), resource (credit memo), context (customer credit), and platform (QuickBooks Online). It distinguishes from sibling tools like create_invoice or create_sales_receipt by specifying 'customer credit'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as create_refund_receipt or create_vendor_credit. No prerequisites or exclusions provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only states 'create a bank deposit' without mentioning side effects, authorization needs, rate limits, or data persistence. An agent has no insight into what happens beyond creation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence, 8 words), which is efficient but sacrifices necessary detail for a complex tool with nested parameters and no output schema. It is not verbose, but it is under-informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested objects, no output schema, no annotations), the description is severely incomplete. It fails to explain what a deposit is in QBO, how line items relate to accounts, or what the response contains. This would hinder an agent's correct usage.
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?
The schema covers descriptions for most parameters (deposit_to_account_ref, line_items, txn_date, private_note), so the description adds no additional meaning. However, the schema coverage is 50% (context signal), meaning half of parameters may lack descriptions. The description does not compensate for this gap.
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 the verb (Create), resource (bank deposit), and context (QuickBooks Online). It is specific enough to distinguish from sibling tools like create_invoice or create_payment, which deal with different financial documents.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., create_transfer, create_journal_entry). There is no mention of prerequisites, required permissions, or scenarios where this tool is inappropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It only says 'delete,' implying mutation, but does not disclose permanence, required permissions, or side effects like concurrency control via SyncToken.
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 sentence with no unnecessary words, making it concise. However, it is too brief and lacks structure to convey additional useful information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested parameters, no output schema, no annotations), the description is insufficient. It omits key context like success/error responses, prerequisite steps, and the effect of deletion.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is low (50%), and the description adds no meaning to parameters. It does not explain what 'Id' and 'SyncToken' represent or how to obtain them, leaving the agent to guess.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Delete') and the resource ('a bill in QuickBooks Online'), making the purpose obvious. However, it does not differentiate from sibling delete tools like delete_bill_payment or delete_invoice.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, and no prerequisites mentioned (e.g., needing to retrieve the Id and SyncToken first). The agent is left without context for proper usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states the action (delete/void) but does not disclose permissions needed, irreversibility, cascading effects on related records, or error handling. This is insufficient for a destructive operation.
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 sentence of 9 words, extremely concise. However, it sacrifices valuable detail that could be added without significant verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's destructive nature, absence of output schema, and lack of annotations, the description is incomplete. It fails to clarify input requirements, return value, or success/error conditions, making it insufficient for proper invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only 'company' has a description). The tool description adds no parameter semantics beyond the schema; it does not explain 'params.idOrEntity' or how to identify the credit memo. This leaves significant ambiguity for parameter usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('delete (void)') and the resource ('credit memo') in the context of QuickBooks Online. It effectively identifies the tool's purpose relative to siblings, which are similarly named for other entities, though it does not elaborate on nuances.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., delete_invoice, delete_vendor_credit). It does not mention prerequisites, use cases, or exclusions, leaving the agent without decision-making support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. The description only states 'Delete (void)' but does not explain side effects, permission requirements, or whether the operation is reversible. This is insufficient for safe usage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is a single sentence, which is concise, but lacks structure. It is front-loaded with the action and resource, but misses important details that would justify a higher score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description provides minimal completeness. It covers the basic purpose but omits return behavior, error handling, and parameter specifics. Adequate for a simple delete tool but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only 'company' parameter described). The description does not add any meaning beyond the schema, and the 'idOrEntity' parameter inside 'params' remains undocumented. For a tool with low schema coverage, the description should compensate but does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (Delete/void) and the resource (refund receipt). However, it does not differentiate from siblings like delete_credit_memo or delete_invoice, which reduces clarity slightly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other delete tools (e.g., delete_credit_memo, delete_sales_receipt). Lacks context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full behavioral burden. However, it only states the basic action without disclosing safety (e.g., read-only, data freshness), permissions, or side effects, which is insufficient for a report generation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no waste, but it is arguably too brief and lacks structured information. It could be improved by front-loading key details without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and partial schema coverage, the description fails to provide sufficient context. It does not explain what the report contains, return format, or any limitations, leaving a significant informational gap for a financial report tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only 'company' has a top-level description; 'params' object lacks one). The description adds no meaning beyond the schema, failing to explain the role of parameters or their relationships, and does not compensate for the missing description.
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 the verb 'Generate' and the specific resource 'Statement of Cash Flows report from QuickBooks Online,' distinguishing it from sibling report tools like get_balance_sheet or get_profit_and_loss.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, context, or exclusions, leaving the agent without decision support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description does not disclose behavioral aspects such as read-only nature, data freshness, pagination, or whether the report is generated on-the-fly. For a report tool with no annotations, this is a significant gap.
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?
Description is one sentence with 14 words, concise and front-loaded. However, it lacks structure or additional details that could aid understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, and description does not specify return format or what 'all account balances' entails. For a report with many sibling report tools, more context is needed to ensure appropriate selection and usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (params object lacks description), and the tool description does not add meaning beyond what the schema provides. Parameters are not explained in relation to the report generation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool generates a Trial Balance report from QuickBooks Online showing all account balances. Verb and resource are specific, but does not differentiate from sibling report tools like get_balance_sheet or get_general_ledger.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives, no prerequisites or when-not-to-use conditions. The description provides no context for selection among sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description only says 'search' implying read-only but does not disclose any behavioral traits like authentication requirements, rate limits, or what data is returned.
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 one short sentence, front-loaded and without extraneous words. It is concise but potentially too terse for clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the input schema (nested object) and lack of annotations or output schema, the description is incomplete. It does not mention pagination, result format, or search capabilities.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (only 'company' has description). The description adds no parameter-level meaning beyond 'using criteria', failing to compensate for the missing schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it searches chart-of-accounts entries, which is a specific verb and resource. However, it does not differentiate from other search_* tools beyond the entity name, and the phrase 'using criteria' is vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other search tools or when not to use it. There are many sibling search tools, but no context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully convey behavioral traits. However, it only states 'search with optional filters' without disclosing whether it is read-only, requires authentication, has pagination, rate limits, or any other behavioral characteristics. This is insufficient for safe and effective use.
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 concise sentence that clearly states the tool's function. However, it sacrifices necessary detail for brevity; adding a bit more context would not reduce conciseness significantly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has nested parameters, no output schema, and no annotations, the description is too minimal. It does not explain what attachables are, the result format, or default behavior when no filters are provided. This leaves the agent without crucial context for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no detail about the parameters beyond the schema. With schema description coverage at 50% (only the 'company' property is described at the top level), the description should compensate but only offers the vague phrase 'optional filters'. It does not clarify the purpose of 'file_name', 'content_type', 'limit', or the structure of the 'params' object.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Search', the resource 'attachables', and the scope 'QuickBooks Online with optional filters'. It effectively distinguishes from sibling tools like create_attachable, get_attachable, etc., but does not elaborate on what attachables are, which is a minor gap.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other search tools like search_bills or search_customers. There is no mention of prerequisites, alternative tools, or context for preferring this tool over siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavioral traits. It mentions 'make inactive' which implies non-permanent deletion, but does not clarify side effects, permissions required, or whether the change is reversible.
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?
The description is a single sentence that is front-loaded with the verb and resource. It contains no extraneous words and efficiently conveys the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a delete operation with two parameters (including a nested object), no output schema, and many siblings, the description is too brief. It lacks clarification on how to identify the bill payment, the exact effect of 'make inactive', and what to expect after deletion.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 50%. The description adds no parameter-level information beyond the schema; the company parameter's description is essentially repeated. The idOrEntity parameter is not described at all.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Delete (make inactive)' and the resource 'bill payment' in QuickBooks Online. It is specific and distinguishes from other delete tools, though it does not explicitly differentiate from siblings like delete-bill.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like update_bill_payment or other delete tools. The description does not mention prerequisites or context for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only says 'Delete' which implies mutation. There is no disclosure of whether the operation is irreversible, requires permissions, or has side effects.
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?
The description is a single sentence, direct and to the point. There is no unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a delete operation with no output schema and minimal annotations, the description lacks critical context such as the format of 'idOrEntity', whether the action is permanent, and any error conditions. It is incomplete for an agent to use confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has two parameters: 'params' (with a nested property 'idOrEntity') and 'company'. The description adds no meaning beyond the schema; it does not explain what 'idOrEntity' should be or how to provide it. Schema coverage is 50% but description does not compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it deletes a time activity in QuickBooks Online. It uses a specific verb and resource, but does not distinguish from other delete tools like delete_invoice or delete_customer.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other delete tools or alternatives. It does not mention any prerequisites or scenarios where deletion is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only states it searches with filters. It does not disclose behavioral traits like read-only nature, pagination, sorting, or authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence), but it is too minimal and does not provide structured information. It earns its place but lacks useful detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and moderate complexity (nested params), the description is incomplete. It does not explain return format, pagination, or how filters work together.
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?
All parameters have descriptions in the schema, so the description adds minimal value beyond restating 'optional filters'. The schema already explains each parameter's purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for classes in QuickBooks Online with optional filters, which is a specific verb and resource. However, it does not differentiate from other search tools beyond the resource name, which is already in the tool name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus siblings like get_class or create_class. The description lacks context about scenarios or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden for behavioral disclosure. It only states 'Search for credit memos' without detailing that it returns a list, pagination, or any side effects. No indication of read-only nature or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, but it omits important details. It is minimally adequate but could be more structured with bullet points or additional context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with multiple parameters, no output schema, and no annotations, the description is incomplete. It does not explain filtering by customer/date, limit, or default behavior, leaving the agent with gaps.
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 coverage is high (all parameters have descriptions), so baseline is 3. The tool description adds no additional parameter meaning beyond what the schema provides. No value added to parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for credit memos in QuickBooks Online, identifying the verb and resource. It distinguishes from siblings like search_invoices or get_credit_memo by specifying the entity type, though it does not differentiate from other credit memo tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like get_credit_memo (for single memo retrieval) or other search tools. The description does not mention prerequisites or context for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but offers only 'Update a bill', omitting behavioral traits like full vs. partial update, authorization needs, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence achieving conciseness, but it is too brief for the tool's complexity, lacking critical information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complex nested parameters, no output schema, and no annotations, the description is completely inadequate for correct agent invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (only company described), and the description adds no meaning to the complex bill object, leaving agents without guidance on required fields or format.
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 the verb 'Update' and the resource 'a bill in QuickBooks Online', distinguishing it from sibling tools like create-bill and delete-bill.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only states the action 'Update' without any behavioral details. With no annotations, it fails to disclose important traits such as the need for sync_token for optimistic locking, permission requirements, or idempotency.
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?
The description is a single, direct sentence with no unnecessary words. It is efficiently front-loaded with the key action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with nested parameters and no output schema, the description is too brief. It omits details on return values, error handling, and important context like the role of sync_token or optional parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50%, and the description adds no meaning beyond what the schema already provides. It does not explain parameter usage or constraints, leaving the agent with incomplete understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'existing refund receipt', making the purpose unambiguous. However, it does not specify which fields can be updated nor distinguish itself from other update tools for different entities, resulting in a slight deduction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus its siblings (e.g., create_refund_receipt, delete_refund_receipt). The description only implies usage for modifying existing records, but lacks explicit context or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states the basic action. It does not disclose behavioral traits like permission requirements, validation rules, side effects (e.g., immediate system impact), rate limits, or error conditions. The tool description carries the full burden for transparency but fails to deliver.
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 sentence that conveys the essential purpose. It is concise and front-loaded, with no unnecessary words. However, it is almost too brief, leaving out important details that could be added without verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and a high number of sibling tools, the description is incomplete. It does not mention what the tool returns (e.g., the created class object ID or details), which is critical for an agent to process the result. The lack of usage context and behavioral details further reduces completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 50% of the parameters with descriptions, but the tool description adds no additional meaning beyond what the schema provides. It does not explain the parent_ref parameter's role in creating sub-classes or the optional company parameter's effect. For a tool with moderate schema coverage, the description should compensate but does not.
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 the tool creates a new class in QuickBooks Online for categorizing transactions. The verb 'Create', resource 'class', and context 'QuickBooks Online for categorizing transactions' are explicit and distinguish it from many sibling create tools like create_account or create_department.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as create_account, create_department, or other classification tools. There is no mention of scenarios where create_class is preferred nor any exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose any behavioral traits such as authentication requirements, rate limits, side effects, or whether the operation is reversible. With no annotations, the description carries the full burden but only states it 'creates', which is already implied by the name.
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 very concise with a single sentence, but it lacks sufficient detail. While it is front-loaded with the essential action, it could benefit from additional context without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested parameters, no output schema) and the presence of many sibling tools, the description is too minimal. It does not explain required employee fields, return values, or how it differs from other create entities.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about the parameters beyond what the schema provides. The schema has 50% coverage (only 'company' has a description), and the description does not explain the required 'params.employee' object or its expected structure.
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 the action (Create) and the resource (employee in QuickBooks Online), making the tool's purpose immediately obvious. It distinguishes itself from sibling tools like create_customer or create_vendor by specifying 'employee'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus the many other create tools (e.g., create_customer, create_vendor). There is no mention of prerequisites, alternative tools, or when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description only states 'Create', which implies a write operation. It does not disclose idempotency, side effects, required permissions, or what the tool returns upon success.
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?
The description is a single sentence with no extraneous words, making it highly concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested objects, many sibling tools, no output schema), the description is too brief. It omits important context such as return value, required permissions, and how the created purchase order interacts with other entities.
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?
The description adds no additional meaning to parameters beyond the schema descriptions, which cover about 50% of parameters (e.g., vendor_ref, line_items). The nested line_items fields lack descriptions, but the description does not compensate for this gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Create' and the resource 'purchase order' in 'QuickBooks Online', making the tool's purpose obvious. It distinguishes this tool from sibling create tools for other entities like invoices or bills.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as when to create a purchase order vs. a bill or purchase. No prerequisites or context for usage are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states the core action without disclosing side effects (e.g., recording payment, updating inventory) or prerequisites. Minimal behavioral context.
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?
The description is a single sentence of 10 words, conveying the essential information with no fluff. It is perfectly concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested objects, many parameters) and absence of annotations and output schema, the description is too minimal. It lacks information on return values, error conditions, prerequisites, and side effects, leaving the agent underinformed.
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?
The input schema provides detailed descriptions for all parameters, achieving high coverage. The description adds no extra meaning beyond the schema, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action ('create'), the resource ('sales receipt'), and the context ('immediate payment sale'), distinguishing it from sibling tools like create_invoice. However, it does not explicitly contrast with alternatives, so a 4 is appropriate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. The phrase 'immediate payment sale' implies usage for point-of-sale transactions, but no exclusion criteria or comparison to other create tools is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; the description only states 'Create' which is a write operation. It fails to disclose any behavioral traits such as required permissions, side effects, or limits beyond what is obvious.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise but lacks structure or additional important details. It is minimally viable but could be more informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of the tool (multiple nested parameters, no output schema, no annotations), the description is too brief. It does not cover what happens after creation, return values, or constraints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. Despite schema description coverage at 50%, the tool description does not explain parameter relationships or usage context.
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 the action 'Create' and the resource 'time activity' with clarification 'time tracking entry' and context 'in QuickBooks Online'. It clearly identifies the tool's purpose among many sibling create tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., update_time_activity, delete_time_activity) or any prerequisites. The description lacks context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure but only states 'Delete (void)' without explaining side effects (e.g., irreversibility, impact on related records, permission requirements).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The single sentence is brief but omits essential details that would make it efficient yet informative; it sacrifices completeness for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of QuickBooks and many sibling tools, the description lacks explanation of return values, error scenarios, and related operations, making it incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (company described, params not). The description adds nothing about parameters; the user must infer that 'idOrEntity' identifies the estimate to delete.
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 the action ('Delete (void)') and the resource ('an estimate in QuickBooks Online'), which is specific and distinguishes it from other delete tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like deleting invoices or voiding estimates through other means, nor any prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It notes 'make inactive' implying a non-destructive deletion, but lacks details on reversibility, permissions, side effects, or return values. For a deletion tool, more transparency is needed.
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, concise sentence that imparts the core purpose without excess. However, it could be slightly more structured to include usage hints.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested object, no output schema) and the presence of many sibling delete tools, the description is too minimal. It does not explain how to identify the item (idOrEntity format), success/failure responses, or any constraints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only 'company' is described). The description adds no explanation for the 'params' object or 'idOrEntity', leaving key parameters undocumented. It does not compensate for the missing schema coverage.
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 the action (delete/make inactive) and the resource (item in QuickBooks Online). It distinguishes from sibling tools by specifying 'item' as the target, which is unique among many delete tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., other delete tools) or when not to use it. The description only states what it does, not the context or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It only says 'delete (void)' but does not disclose side effects such as voiding a payment might affect related invoices or transactions. Behavioral implications of voiding are not explained.
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 concise sentence that is front-loaded with the key action. However, it could have included more structured information without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of QuickBooks payment deletion (potential side effects, no output schema), the description is too brief. It lacks guidance on return values, confirmation, or effects on related records.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (only 'company' has description). The description does not explain 'params' or 'idOrEntity'. It adds no meaning beyond the schema, leaving half the parameters undocumented.
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 the action (delete/void) and the resource (payment in QuickBooks Online). It differentiates from sibling delete tools by specifying 'payment' which is distinct from other deletable entities like bills, invoices, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like delete_bill_payment. No prerequisites or conditions (e.g., payment must be unapplied) are mentioned. The description lacks usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states 'Delete', omitting permanence, permission requirements, cascading effects, or return value. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (6 words) and thus concise, but it omits necessary information, making it under-specified rather than appropriately sized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should indicate return behavior or confirmation. It also fails to explain the company parameter context or the nested params structure. Incomplete for a deletion tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (only 'company' described), but the description adds no parameter details. It does not clarify the 'idOrEntity' parameter or any constraints, leaving the agent with incomplete information.
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 the action ('Delete') and the resource ('purchase order') with context ('QuickBooks Online'). It is specific and distinguishes from sibling delete tools for other entities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool vs alternatives (e.g., other delete tools), prerequisites, or limitations such as whether deletion is allowed for approved purchase orders.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It only states that the tool deletes/voids, but fails to disclose behavioral traits such as irreversibility, permission requirements, side effects on related entities, or what 'voiding' implies. This is inadequate for a mutation tool.
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 very short and front-loaded, stating the core purpose in a single sentence. While concise, it could include essential details without being verbose. It earns its place but leaves gaps.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is too minimal. It does not explain the return value, error conditions, or what happens after deletion. For a tool with nested parameters and no output schema, the description is incomplete for safe and correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50%, with only the 'company' parameter having a description. The description does not explain the 'params' object or the required 'idOrEntity' property. It adds minimal meaning beyond the schema. The term 'void' hints at the action but does not clarify parameter semantics.
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 the action 'Delete (void)' and the resource 'sales receipt', with the context 'in QuickBooks Online'. It unambiguously distinguishes from sibling delete tools targeting other entities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. There is no mention of prerequisites, constraints, or situations where a different tool might be more appropriate. The description is insufficient for an AI agent to decide when to invoke this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose any behavioral traits such as irreversibility, required permissions, or effects on related records. Since no annotations exist, the description carries full burden but provides only a minimal statement.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, but it sacrifices necessary detail for brevity. While not overly long, it omits important information about parameters and usage, making it minimally adequate.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a delete operation with no output schema and incomplete parameter documentation, the description should provide more context (e.g., how to identify the vendor credit, side effects). It is insufficient for an agent to use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. The parameter 'idOrEntity' remains undocumented in both the schema and description, and the description does not clarify expected values or format. Schema coverage is 50%, but description fails to compensate.
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 the verb 'Delete' and the resource 'vendor credit', making the tool's purpose immediately apparent. It distinguishes itself from sibling delete tools by specifying 'vendor credit' rather than a generic 'delete'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus other delete tools (e.g., delete_invoice, delete-bill). The description lacks context about prerequisites or alternatives, leaving the agent without decision-support.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It only says 'Retrieve' implying read-only, but discloses no behavioral traits such as permissions, rate limits, or return structure.
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, concise sentence without wasted words. It is front-loaded with the key action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get-by-ID tool with no output schema, the description is adequate but minimal. It does not explain the return format, error cases, or missing ID scenarios, leaving gaps for a complete understanding.
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?
The schema already describes both parameters with basic descriptions (Class ID, company realm ID). The tool description adds no additional meaning, so it meets the baseline given moderate schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb (Retrieve), resource (a specific class from QuickBooks Online), and method (by ID). It is clear and distinguishes from search_classes which searches without an ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidelines provided. The description does not specify when to use this tool vs. search_classes, nor does it mention prerequisites like having the class ID.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It only says 'retrieve', implying read-only, but does not disclose any behavioral traits like authentication, rate limits, error handling, or what happens if the company does not exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is only a single sentence, but it is under-specified. It lacks necessary details like usage guidance and parameter context, making it too brief for the required information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite a simple tool with good schema coverage, the description does not explain what 'company information' includes, the response structure, or that the tool supports specifying a company. Missing critical context for effective use.
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?
The schema already provides descriptions for both parameters (company_id and company), so coverage is high. The tool description adds no additional meaning beyond the schema, thus a baseline score of 3 is appropriate.
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 the verb 'Retrieve' and the resource 'company information' from QuickBooks Online. It is specific and distinguishes from siblings like update_company_info and other get_* tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as update_company_info. It does not mention prerequisites, use cases, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must disclose behavioral traits. It only states the basic action without mentioning idempotency, safety, or authentication requirements. The agent learns nothing beyond the action.
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?
Single sentence, no wasted words. However, it could be slightly more informative without becoming verbose, e.g., mentioning it retrieves the full credit memo record.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no annotations. The description does not mention return value structure, error conditions (e.g., not found), or that it is a read operation. For a simple get tool, this is inadequate completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50%, meaning half of the parameters lack descriptions in the schema. The tool description adds no additional meaning beyond what the schema already provides for the covered parameters, and does not compensate for the uncovered parameter.
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 the verb 'Get', the resource 'credit memo', and the retrieval method 'by ID'. It distinguishes from sibling tools like search_credit_memos (which lists multiple) and other get tools by specifying 'single credit memo'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as search_credit_memos. The description does not specify prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full behavioral burden. It implies a read-only report generation, but does not disclose any side effects, authentication needs, rate limits, or data modification potential. This is insufficient for an agent to understand implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence (15 words), but it could be slightly expanded to include key behavioral or usage hints without losing conciseness. It is not verbose but lacks some essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has nested parameters and no output schema, the description is insufficient. It does not mention the report's output format, pagination, or any defaults (e.g., if all customers are included when 'customer' is omitted). The agent remains uncertain about the result structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no meaning beyond the input schema. The schema already provides descriptions for 'start_date', 'end_date', 'customer', 'summarize_column_by', and 'company'. The tool description does not explain how parameters interact or any constraints (e.g., date range format validity).
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 the verb 'Generate' and the resource 'Customer Sales report from QuickBooks Online' and specifies the output is 'sales by customer.' This distinguishes it from sibling tools like get_profit_and_loss or get_customer_balance.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., get_profit_and_loss, get_customer_balance). There is no mention of prerequisites, limitations, or when it is inappropriate to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states 'Get', implying read-only, but offers no details on authentication, rate limits, or error behavior.
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 sentence, concise and front-loaded. However, it is so brief that it sacrifices useful detail, earning a high but not perfect score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get tool with no output schema, the description lacks mention of return value structure, error handling, or limitations, making it incomplete for an agent to fully understand behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only 'company' described). The description does not clarify the meaning of the 'id' parameter or add value beyond the schema, failing to compensate for the gap.
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 'Get an employee by Id from QuickBooks Online' clearly identifies the action (get) and resource (employee by Id), distinguishing it from sibling tools like search_employees which are for searching.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as search_employees, nor does it specify prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits but only states the basic operation. Missing details on read-only nature, error handling, or ID validation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, concise but too brief. It front-loads the purpose but could be more structured without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema or annotations, the description is incomplete. It does not explain return format, error scenarios, or common fields. More context is needed for successful invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only company described). The tool description mentions Id but adds no format or meaning beyond the schema. The id parameter has no description in schema or description.
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 the action (Get), resource (estimate), and method (by Id) with scope (QuickBooks Online). It distinguishes from siblings like search_estimates.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like search_estimates or other get_* tools. The description lacks context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose read-only nature, potential performance implications, or any side effects beyond generating a report.
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?
Single sentence, no redundancy, but could include more detail without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and description omits important behavioral details like pagination, date range limits, or response format, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite schema descriptions for parameters, the tool description adds no extra meaning to parameters like start_date, end_date, or sorting. With 50% schema coverage, more description needed.
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 it generates a General Ledger report from QuickBooks Online with detailed transaction history, distinguishing it from other report tools like balance sheet or profit and loss.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as get_trial_balance or get_profit_and_loss. Lacks context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It only states a retrieval operation but omits traits like idempotency, authentication requirements, or whether it is read-only. The agent cannot assess safety or side effects from this description alone.
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?
The description is a single, front-loaded sentence that wastes no words. It efficiently conveys the core action and resource, achieving excellent conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 parameters, no output schema, no annotations), the description covers the basic operation. However, it omits expected return structure or additional context like entity scope, leaving some gaps that a richer description could fill.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (company described, id not). The description adds no meaning beyond the schema; it does not clarify the format or purpose of the 'id' parameter. With low coverage and no additional description, the agent gains no extra insight.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get a purchase') and the resource ('by Id from QuickBooks Online'), making the purpose unambiguous. However, it does not differentiate between similar entities like purchase orders, but the tool name and context sufficiently identify the target.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as search_purchases or get_purchase_order. There is no mention of prerequisites, limitations, or exclusion criteria, leaving the agent without context for proper selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It merely says 'retrieve', implying a read operation, but doesn't disclose permissions, errors, or other behavioral traits beyond the name.
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, clear sentence with no unnecessary words. However, it could be slightly more informative without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a minimal description, the tool lacks essential context such as return structure, error conditions, or what a tax agency represents. It is incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not describe any parameters. Schema coverage is 50%, but the description adds no extra meaning to the parameters. The schema already provides minimal descriptions for 'id' and 'company'.
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 the verb 'retrieve', the resource 'tax agency', and the method 'by ID'. It distinguishes from sibling tools like search_tax_agencies which search, and other get tools for different entities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description lacks any guidance on when to use this tool versus alternatives like search_tax_agencies. No prerequisites or context are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It only states 'retrieve', which indicates a read operation, but does not mention side effects, authentication needs, or any constraints beyond that.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it lacks substantive detail. While brevity is good, the trade-off is insufficient information for an agent to use the tool effectively.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (retrieve by ID) and no output schema, the description is minimally adequate. However, for a tool with two parameters (one nested) and siblings that perform similar functions, more context would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50%, and the description does not add meaning beyond the schema. It mentions 'by ID' but does not explain the 'company' parameter or any other parameter details. The description fails to compensate for incomplete schema documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the verb 'Retrieve', the resource 'tax code', and the method 'by ID'. It effectively conveys the main function, though it does not distinguish from the sibling 'search_tax_codes' which retrieves multiple codes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you have a specific ID, but provides no explicit guidance on when to use this tool over alternatives like 'search_tax_codes'. No exclusions or context are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of transparency, but it does not disclose whether the operation is read-only, requires any permissions, or what happens if the ID is invalid. It merely states the action.
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 one sentence and efficient, but it omits important context that could be included without excessive length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool with minimal parameters and no output schema, the description lacks details about return values, error handling, or any behavioral notes, making it incomplete for an agent to fully understand usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
While the schema covers both parameters with descriptions, the tool's description adds no additional semantics beyond what the schema provides. Given the reported 50% schema coverage, the description should compensate but does not.
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 that the tool retrieves a vendor credit by ID from QuickBooks Online, specifying the verb 'get' and resource 'vendor credit', which distinguishes it from search and update tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like search_vendor_credits or when not to use it, and lacks any mention of prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full responsibility for behavioral disclosure. It only states the basic function, omitting details about error handling (e.g., when invoice not found), permissions required, or whether the response includes the full invoice object. No output schema is provided either.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no waste, but it sacrifices important information for brevity. For a read operation, it is minimally adequate but lacks behavioral and parameter details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has two parameters, no output schema, and no annotations, the description is incomplete. It does not cover return values, error states, or preconditions. The sibling tools list is large but no comparison is provided.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Parameter description coverage is 50%: only the 'company' parameter has a description in the schema. The description does not add any further meaning for 'invoice_id' beyond what is in the schema (type string, minLength 1). It does not compensate for the missing schema descriptions.
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 the verb 'Read', the resource 'single invoice', and the method 'by its ID'. This distinguishes it from sibling tools like search_invoices (which search multiple) and create_invoice (which creates).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as search_invoices or other read tools for related entities. It does not specify prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits, but it only says 'search with criteria.' It omits pagination, rate limits, or behavior with large result sets.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, but it is under-specified for the tool's complexity. It is concise but lacks necessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complex input schema and no output schema, the description fails to explain return values, pagination, or how to use optional parameters like limit and offset.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50%, and the description adds no meaning beyond the schema. It does not explain the purpose of limit, offset, fetchAll, or count.
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 it searches estimates in QuickBooks Online, distinguishing it from create/update/get tools. It explicitly mentions matching criteria.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool over alternatives like get_estimate or other search tools. No mention of when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, and the description only states 'search invoices using criteria' without disclosing behavioral traits such as pagination, result format, rate limits, or side effects. The description provides minimal transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise, but it lacks important details that would justify its brevity. It is efficiently short but at the cost of completeness and clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a search tool with a nested 'criteria' parameter and no output schema, the description is incomplete. It fails to specify what the search returns, how to structure criteria, or any usage constraints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (company described, params not). The description adds no meaning beyond 'using criteria' and does not explain the structure or possible values of the criteria parameter. The parameters' semantics remain largely undocumented.
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 the tool searches invoices in QuickBooks Online using criteria, specifying the resource (invoices) and action (search). It distinguishes from sibling search tools by focusing on invoices, though it could be improved by contrasting with read_invoice.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like read_invoice or other search_* tools. The description lacks any context about use cases or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only states the action without mentioning read-only nature, return format, pagination, or authentication requirements, leaving significant gaps.
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?
The description is a single sentence with no wasted words. It is appropriately sized for a straightforward search function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is too brief given the tool's complexity and the presence of many siblings. It lacks information about return values, filtering behavior, and when to choose this tool over others.
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?
The description does not add meaning beyond the input schema, which already documents parameters adequately. With schema description coverage at 50%, the minimal description neither enhances nor degrades parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches for payments in QuickBooks Online, specifying the verb and resource. However, it does not differentiate from many sibling search tools (e.g., search_invoices, search_bill_payments), which may cause confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description lacks context for when to choose search_payments over other search tools, and no exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries full burden. It does not disclose that this is a read-only operation, nor does it mention pagination, rate limits, or what happens on failure. The minimal description provides insufficient behavioral context.
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 concise sentence with no wasted words. However, it is overly brief and could benefit from added context without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the nested input schema and no output schema, the description is incomplete. It does not explain the return format, pagination, or how to effectively use the complex filter structure. More details are needed for an AI to invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50%, but the description does not add any parameter meaning beyond the schema. It only says 'match given criteria', which is already implied. The schema is detailed, but the description fails to compensate for the coverage gap.
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 'Search vendors in QuickBooks Online' with the specific verb 'Search' and resource 'vendors', and adds filtering context ('that match given criteria'). It distinguishes from sibling tools like get-vendor (individual retrieval) and create-vendor (creation).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., get-vendor, other search tools) or when not to use it. The description lacks any usage context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits but only says 'Update'. It does not mention that the tool requires a sync_token for concurrency, that it modifies existing data, or what the response looks like. Critical behavioral details are missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words. However, it is overly minimal and lacks informative content, which is a trade-off between conciseness and completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description should provide more context about behavior, required fields, and side effects. The current description is insufficient for a mutation tool, leaving the agent to infer critical details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The top-level schema coverage is 50% (params lacks description), but the description adds no parameter meaning beyond the schema. It does not explain how parameters like file_name, note, or category affect the resource, nor does it clarify the role of sync_token or company.
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 the action ('Update'), the resource ('attachable'), and the system ('QuickBooks Online'). It effectively distinguishes from sibling tools like create_attachable, delete_attachable, and get_attachable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, such as when to update vs create or delete. There is no mention of prerequisites or context for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden but only says 'update'. It does not disclose whether it's partial or full update, whether it returns the updated object, or any safety/crucially behavior like required fields.
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, concise sentence with no wasted words. However, it could include more useful information without becoming overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with a nested parameter object and no output schema, the description is too minimal. It does not explain how to identify which bill payment to update or what the params object should contain, leaving significant gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers 50% of parameters with descriptions (company), but the core 'params' object has no description. The tool description adds no additional parameter semantics beyond what 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 explicitly states the verb 'update' and the resource 'bill payment', clearly distinguishing it from sibling tools like create, delete, or get for the same resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., create_bill_payment, delete_bill_payment). No prerequisites or context for invocation are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a mutation operation ('Update') but provides no additional behavioral context such as required permissions, reversibility, effect on omitted fields, or response behavior. With no annotations, the description fails to disclose important traits beyond the verb.
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 efficient sentence with no filler. However, it lacks front-loading of key constraints or context, and it could be slightly more structured for clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (nested object, many updatable fields, concurrency token, no output schema, no annotations), the description is insufficient. It omits important details like partial update semantics, required fields, and return value, leaving gaps for the agent.
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?
The input schema already provides descriptions for all parameters, including nested fields. The description does not add meaning beyond stating the tool's general purpose. For a tool with high schema coverage, a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Update' and the resource 'company information in QuickBooks Online'. It is specific enough to distinguish from unrelated tools but does not differentiate from other update tools like update_account or update_customer.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. For instance, there is no mention of prerequisites, context for use, or when not to use it, leaving the agent to infer from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description is minimal. It does not disclose any behavioral traits such as whether it performs a partial or full update, required permissions, side effects, or constraints. The description fails to provide the necessary behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, which is concise. However, it lacks structure and does not front-load key information. A slightly longer description with more detail could be more helpful without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of updating a journal entry (nested objects, no output schema, missing annotations), the description is insufficient. It does not indicate what data is required, what the tool returns, or any constraints, leaving the agent under-informed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has two parameters, but only 'company' has a description (schema coverage 50%). The description does not explain the 'params' object or its 'journalEntry' property, nor does it add any meaning beyond the schema. The description does not compensate for the low schema coverage.
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 is 'Update a journal entry in QuickBooks Online.' It clearly states the action (Update) and the resource (journal entry), distinguishing it from sibling tools like create_journal_entry, delete_journal_entry, get_journal_entry, and search_journal_entries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. The sibling list includes many update tools, but the description gives no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies mutation but does not disclose side effects, permission requirements, or concurrency behavior. The sync_token parameter hints at optimistic locking, but this is not explained in the text. With no annotations, the description should compensate but does not.
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, front-loaded sentence with no extraneous words. While concise, it sacrifices necessary detail; a slightly longer description would improve completeness without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (concurrency control, multiple fields, optional company context), the description is too brief. It does not mention error conditions, return values, or the impact of setting 'active' to false. An output schema is absent, so the description should provide more behavioral context.
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?
The input schema provides descriptions for all parameters (id, sync_token, name, active, company), so the description adds minimal value. It could have explained the role of sync_token or the effect of the 'active' flag, but it does not. Baseline is set to 3 due to high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update') and the resource ('payment method') within QuickBooks Online. It is specific enough to distinguish from other update tools for different entities, though it does not list the updatable fields.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. Context such as prerequisites (e.g., existing payment method, need for sync token) is omitted, leaving the agent to infer from the parameter requirements.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It only says 'Update,' implying mutation, but it does not disclose side effects, required permissions, idempotency, or what happens to existing data. The description is insufficient for a mutation tool without annotations.
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 concise sentence that quickly conveys the tool's purpose. While it lacks structured elements like bullet points or context, it is efficient and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of sibling time activity tools (create, get, delete), the description does not differentiate when to use update. It also lacks details on return values (no output schema) and preconditions. The description is too minimal for complete context.
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?
The input schema already provides descriptions for all parameters, covering 100% of them (contrary to the 50% coverage indicated). The description adds no additional semantics beyond the schema, so it meets the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Update a time activity in QuickBooks Online' clearly states the action and resource, distinguishing it from sibling tools like create_time_activity or delete_time_activity. However, it lacks any additional context about what a time activity is.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., create_time_activity or update_time_activity via other methods). No prerequisites or contexts are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that deletion actually makes the customer inactive, which is important behavioral detail. However, does not explain side effects on associated data, reversibility, or permission requirements.
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?
Extremely concise single sentence with no redundancy. Could be slightly expanded with parameter hints without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks context about identifying the customer, expected output, error scenarios, and relationship to other operations. Given no output schema and sparse annotations, the description fails to provide sufficient completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Description adds no information about parameters despite schema coverage being only 50%. Does not explain 'idOrEntity' role or usage. The schema provides partial description for 'company', but the description itself contributes nothing.
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?
Description clearly states the action (delete/make inactive) and the resource (customer in QuickBooks Online). It distinguishes this tool from siblings like create_customer, update_customer, and other delete tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like update_customer to inactivate, or when not to use it. Does not mention prerequisites or consequences.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry the burden. It does not disclose whether the tool returns the created department object, whether it is idempotent, or what happens on failure (e.g., duplicate name). Only the action 'Create' is stated.
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, clear sentence that efficiently conveys the tool's purpose. However, it could be restructured to front-load key information or include bullet points for parameter details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a creation tool with nested parameters and no output schema, the description is too brief. It omits crucial details such as return value, error behavior, and permission requirements, which are necessary for an agent to use the tool correctly.
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 50% (only top-level parameters have descriptions; nested 'params' object lacks description). The tool description adds no additional meaning beyond the schema, so it meets baseline but does not compensate for the coverage gap.
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 the verb 'Create', the resource 'department', and the context 'in QuickBooks Online for location/department tracking'. It distinguishes this from sibling create tools by specifying the target entity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternative create tools (e.g., create_class, create_customer). No mention of prerequisites, such as whether a parent department must exist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only indicates a write operation ('Create') without disclosing behavioral traits such as permissions, idempotency, side effects, or response format, which is insufficient given the absence of annotations.
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 concise sentence that efficiently conveys the core purpose without extraneous information, though it could be slightly more structured by including key usage hints.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description fails to address important contextual details like return behavior, uniqueness constraints, or the optional 'company' parameter, leaving significant gaps for an agent to operate effectively.
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?
The input schema already provides descriptions for both parameters (name and type) and the company field; the description adds no additional parameter meaning beyond listing examples, thus not improving upon the schema's coverage (50%).
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 the action (creating a new payment method) and provides concrete examples (Cash, Check, Credit Card), effectively distinguishing it from sibling creation tools that target different entities.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternative creation tools, nor are any prerequisites or contexts for usage mentioned, leaving the agent to infer suitability.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, yet the description fails to disclose behavioral traits such as whether the operation is idempotent, what permissions are needed, rate limits, or what the response contains. For a write operation, this is a significant gap.
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?
The description is a single, well-structured sentence that immediately conveys the tool's purpose. It is appropriately concise with no unnecessary words, earning its place as a front-loaded summary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has nested parameters and no output schema, the description is too brief. It omits critical context such as the effect on QuickBooks, whether a refund receipt is linked to an original sale, or what happens to inventory/accounts. A more complete description would greatly improve usability.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no additional meaning beyond the parameter names already present in the schema. With schema description coverage reported as 50%, the description should compensate but does not. It does not explain the purpose or constraints of individual parameters like customer_ref or line_items.
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 the action (create), the resource (refund receipt), and the context (QuickBooks Online), making it unambiguous. It effectively distinguishes from sibling tools like create_invoice or create_credit_memo by naming the specific refund receipt entity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like create_credit_memo or create_vendor_credit. Without context on prerequisites or typical use cases, an agent may struggle to choose the correct tool among many similar refund-related options.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the basic purpose without disclosing side effects, return values, error conditions, or required permissions. Inadequate for a mutation tool.
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?
A single sentence is concise and to the point. No extraneous information, but could benefit from slightly more detail without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters (including nested objects) and no output schema, the description is too minimal. It does not explain the effect of creating a vendor credit or what the response looks like. Incomplete for an agent to fully understand the tool.
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 descriptions cover all parameters but the description adds no extra meaning. With 50% coverage (per context), the description could compensate but does not. However, schema itself provides enough for basic understanding.
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 the action ('Create') and resource ('vendor credit') with context ('in QuickBooks Online'). This is specific and distinguishes it from siblings like 'create_credit_memo'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as 'create_credit_memo' or other create tools. Missing context about prerequisites or typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist; description only says 'delete' without disclosing whether it's hard or soft delete, permissions required, or side effects. Agent cannot assess impact.
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?
Single sentence, efficient and no wasted words. Could be expanded slightly for completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no annotations; description fails to explain return value or effect on system. Incomplete for a mutation tool.
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?
Input schema already provides descriptions for all parameters (id, sync_token, company). The description adds no extra meaning 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 the action ('Delete'), the resource ('attachable'), and the context ('QuickBooks Online'), making it distinct from sibling delete tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like update_attachable or when deletion is appropriate. Missing prerequisites or consequences.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry the full behavioral burden. It only states the action without explaining repercussions (e.g., voided invoice effects, permissions needed, or irreversible nature).
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?
A single sentence with no redundancy, efficiently conveying the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no explanations of return value, error handling, or confirmation. For a destructive operation, this is insufficiently informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (company has description, idOrEntity does not). The description adds no parameter details beyond what the schema provides, failing to compensate for the undocumented idOrEntity parameter.
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 the action ('Delete (void)') and the resource ('an invoice in QuickBooks Online'), distinguishing it from other delete tools for different entities (e.g., delete_bill).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like update_invoice (which might also change invoice status) or search_invoices to find the invoice first. No prerequisites or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavioral traits. It only hints at soft delete with 'make inactive,' but does not explain exact behavior, required permissions, reversibility, or side effects on related data. The description is insufficient for the agent to understand the tool's full impact.
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?
The description is a single, front-loaded sentence with no redundant words. It efficiently conveys the core purpose without extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has two parameters (one undocumented), no output schema, and no annotations, the description is too minimal. It omits how to use the parameters (especially idOrEntity), expected outcomes, and any context about QuickBooks Online behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 50%: the 'company' parameter has a description, but 'idOrEntity' does not and the tool description does not clarify it. The description adds no meaning beyond the schema, leaving the agent uncertain about how to specify the purchase to delete.
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 that the tool deletes (makes inactive) a purchase in QuickBooks Online, specifying the verb and the resource. It distinguishes from sibling delete tools by naming the entity ('purchase'), making it easy to select among many similar delete tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., other delete tools), prerequisites, or when not to use it. The description lacks any context about typical use cases or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that the operation is a soft delete (makes inactive rather than hard-delete). With no annotations, this adds value. However, it does not mention required permissions, side effects, or any other behavioral aspects.
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?
Two sentences, front-loaded with the key action and important nuance (soft delete). No unnecessary words, efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 2 parameters (one nested), no output schema, and no annotations, the description covers the basic action but misses details on vendor parameter semantics, response behavior, and how to obtain the SyncToken. Adequate but with clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (only 'company' has description; 'vendor' is undocumented). The description does not explain the Id and SyncToken parameters, which are crucial. It adds no meaning beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (delete/make inactive) and resource (vendor in QuickBooks Online), and distinguishes it from hard-delete by clarifying it marks Active: false. However, it does not explicitly differentiate from other delete-* sibling tools beyond the resource name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., directly updating vendor status). No mention of prerequisites, limitations, or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must fully convey behavioral traits. It only states it generates a report, but does not mention that it is read-only, whether it requires specific permissions, what happens to data, or any rate limits. This is insufficient for a tool with no annotation support.
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?
The description is a single sentence that efficiently conveys the tool's purpose. No unnecessary words or redundancy. It is well-structured and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a report generation tool with no output schema and no annotations, the description is too brief. It lacks details on what the report contains, how to interpret results, or any operational context. The two parameters are not explained beyond what is in the schema, leaving significant gaps for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add any meaning beyond the schema. The schema has descriptions for sub-parameters, but the tool description itself does not explain how to construct the params object or the significance of parameters. Given the context of 50% schema description coverage, the description should compensate but does not.
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 the tool generates an Aged Payables report from QuickBooks Online, showing outstanding vendor bills. The verb 'Generate' and resource 'Aged Payables report' are specific, and it distinguishes from sibling tools like get_aged_receivables.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., get_vendor_balance or get_vendor_expenses). There is no mention of prerequisites, typical use cases, or scenarios where this tool is not appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description bears full responsibility for behavioral disclosure. It only states 'retrieve by ID' without mentioning read-only nature, permissions, or return value characteristics.
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, efficient sentence with no waste. However, it could be slightly more informative without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and annotations, the description is minimal. It does not explain return values, error handling, or the role of the 'company' parameter in multi-company contexts.
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?
The input schema already provides clear descriptions for both parameters ('id' and 'company'), achieving 50% coverage. The description adds no further meaning beyond the schema, so a baseline score of 3 is appropriate.
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 the action (retrieve), resource (department), and scope (by ID). It effectively distinguishes from sibling tools like search_departments and create_department.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as search_departments (for listing) or create/update department tools. The description lacks context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits such as read-only nature, authentication requirements, rate limits, or side effects.
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 sentence with no wasted words. It is appropriately sized but could include more context without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is minimal. It does not specify return format, error conditions, or behavior when the ID is not found. Adequate for a simple retrieval but lacks completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (2 parameters with descriptions). The description adds no additional meaning beyond the schema; it only mentions 'by ID' without explaining the 'company' parameter.
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 the action (retrieve), resource (payment method), and method (by ID). It distinguishes from sibling tools like search_payment_methods which retrieve multiple records.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., search_payment_methods). The description does not mention prerequisites or context for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only indicates search with optional filters but omits details like read-only nature, pagination, rate limits, or default behavior.
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?
Single sentence, no wasted words; efficiently states core purpose, though could benefit from minor expansions.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks information on return format, pagination, or result limits; important for a search tool with no output schema.
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?
Input schema descriptions already cover parameter meanings adequately; the description adds no extra value, so baseline 3 is appropriate given the schema coverage.
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?
Description clearly states the action (search), resource (payment methods), and platform (QuickBooks Online), effectively distinguishing from sibling tools like get_payment_method or create_payment_method.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use search vs. get or how to leverage filters; lacks context for decision-making among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits such as read-only nature, authentication requirements, or any side effects. The description is silent beyond the basic search functionality.
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, front-loaded sentence without wasted words, though it could be more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, so the description should clarify what is returned (e.g., list of tax agencies). It does not, leaving the agent with an incomplete understanding of the tool's output.
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?
The input schema has 50% coverage (only 'company' has a top-level description). The description adds no additional meaning beyond the schema for the nested parameters, only stating 'with optional filters' which is generic.
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 the verb 'Search' and the resource 'tax agencies' in QuickBooks Online, and distinguishes from siblings like search_tax_codes and search_tax_rates.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, nor any prerequisites or context for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as whether the operation is read-only, authentication requirements, or pagination behavior. It merely states 'Search', implying read-only but not explicitly.
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 extremely concise with a single sentence. However, it lacks structure and does not front-load the most critical information like the source system or scope.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with nested parameters and no output schema, the description is incomplete. It does not explain the return format, pagination, or any constraints. The minimal description fails to compensate for the lack of annotations.
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?
The input schema already describes all parameters with clear descriptions. The description adds the phrase 'with optional filters', which mirrors the schema. Given full schema coverage, the description adds minimal value.
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 the verb 'Search' and the resource 'tax rates in QuickBooks Online', which is specific and distinguishes from sibling tools like 'get_tax_rate' or 'search_tax_codes'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as 'get_tax_rate' for a single tax rate or other search tools. No mention of prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavioral traits. It merely states 'Update an existing class' without mentioning concurrency via sync_token, return value, idempotency, error handling, or required permissions. The minimal description fails to inform the agent about important side effects or constraints.
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, front-loaded sentence that efficiently states the tool's main action. It contains no wasted words. However, it is slightly too brief given the tool's complexity, but the conciseness itself is good.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has a nested parameter object, 5 total parameters, no output schema, and no annotations, the single-sentence description is insufficient. It does not explain required fields (id, sync_token with concurrency role), optional fields (name, active), or the company targeting. The agent lacks essential context for correct invocation.
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?
The description adds no meaning beyond the input schema. The schema already describes all parameters with descriptions (id, sync_token, name, active, company). Although the context indicates 50% coverage, the description does not clarify parameter usage, formatting, or relationships. It does not hinder understanding but also does not enhance it.
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 uses a specific verb 'Update' and a clear resource 'existing class in QuickBooks Online'. It distinguishes itself from sibling tools like create_class or search_classes by indicating it modifies an existing entity. The purpose is immediately understood.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus its alternatives (e.g., create_class for new classes, get_class for retrieval, or search_classes for listing). There are no explicit conditions, prerequisites, or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states the update action but does not mention mutability, concurrency via sync_token, deactivation capability, or that the department must already exist. Missing critical safety context for a mutation tool.
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?
The description is a single, front-loaded sentence with no redundant words. It is efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a nested parameter object and concurrency mechanism but no output schema. The description provides no details about return values, error behavior, or the need for an existing department. Incomplete for a mutation tool of this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (company has description, params object does not). The tool description adds no parameter meaning beyond what is in the schema. It does not clarify the purpose of params or the optionality of company.
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 the verb 'update', the resource 'department', and the context 'in QuickBooks Online'. It unambiguously describes what the tool does and distinguishes it from create_department and search_departments.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus other update tools (e.g., update_account). No prerequisites or conditions for use are mentioned. The description lacks any indication of when to apply the update.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It states 'update' implying mutation but does not describe destructive behavior, permission requirements, partial vs full update semantics, or side effects. The required sync_token for optimistic locking is not explained in the description.
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, concise sentence that immediately conveys the purpose. It is front-loaded with the key action and resource, avoiding unnecessary words. However, it could be expanded slightly to include critical usage hints without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks completeness for a mutation tool. It does not explain the return value (no output schema), error conditions, or the need for a sync_token to prevent conflicts. Given the complexity of updating a sales receipt in QuickBooks, more contextual details are needed for correct usage.
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?
The input schema provides descriptions for all parameters (e.g., 'Sync token for optimistic locking'). With high schema coverage, the description adds no extra meaning. Baseline of 3 is appropriate as the schema already documents parameter semantics.
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 'Update an existing sales receipt in QuickBooks Online', specifying the verb (update), resource (sales receipt), and system (QuickBooks Online). This distinguishes it from sibling tools like create_sales_receipt, delete_sales_receipt, and get_sales_receipt.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites like needing a valid sync_token for optimistic locking nor when to avoid updating. Without any usage context, the agent cannot determine appropriate scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavioral traits. It only states 'Update' without detailing requirements, failure modes, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence is concise but not front-loaded with critical details; no structure to aid scanning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema; description omits return values, error conditions, and concurrency behavior. Incomplete for a mutation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Description adds no meaning beyond the input schema. With 50% schema coverage, it should compensate but does not.
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?
Description clearly states the action (Update), resource (payment term), and scope (QuickBooks Online). It distinguishes from sibling tools like create_term or get_term.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implied usage for updating existing terms, but no explicit guidance on when to use vs alternatives, prerequisites, or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only indicates a write operation, but fails to mention side effects (e.g., duplicate handling), permissions, rate limits, or return format. This is insufficient for an unannotated tool.
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 sentence that efficiently conveys the tool's purpose. It is front-loaded and contains no fluff, but could benefit from additional context without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is insufficient. It does not explain return values, error conditions, or provide guidance on account types or constraints. The tool has moderate complexity with required nested parameters and many siblings, yet the description is minimal.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 50% (only 'company' has a description). The description adds no parameter-specific details beyond what the schema provides. The 'params' object's sub-properties (name, type, sub_type, description) are not explained, leaving the agent without meaning.
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 the verb 'Create' and the resource 'chart-of-accounts entry in QuickBooks Online,' which is specific and distinct from other create tools (e.g., create_customer, create_invoice) and update tools (update_account).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives (e.g., update_account for existing accounts) or mention prerequisites or conditions. The usage is implied by the name but lacks explicit context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states the basic action without disclosing side effects (e.g., affecting accounts receivable), required permissions, idempotency, or rate limits. The description adds no behavioral context beyond the obvious.
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?
The description is a single sentence of 12 words, with no wasted or redundant information. It is front-loaded with the essential purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a complex nested input schema (e.g., 'line' items linking to invoices) and no output schema or annotations. The description does not explain the relationship between parameters, expected behavior (e.g., what happens if line is omitted), error conditions, or return values. It is insufficient for an effective agent usage.
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?
The input schema already has detailed descriptions for most parameters, including nested objects. The tool description does not add any additional meaning beyond the schema, so the baseline score of 3 applies given the high schema description coverage.
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 the verb 'create' and the resource 'payment', with the parenthetical 'receive money from customer' distinguishing it from other create tools like create_invoice or create_sales_receipt. It also specifies the context 'in QuickBooks Online'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., create_bill_payment, create_sales_receipt). The description does not mention prerequisites, limitations, or typical use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavioral traits. It only states the basic action without explaining whether the transfer is immediately applied, requires authorization, or what side-effects occur (e.g., account balances update).
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?
A single, focused sentence with no extraneous words. It is front-loaded with the key action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the financial nature and 5 parameters, the description is insufficient. It omits return value information, error handling, default behaviors (e.g., what happens if txn_date is omitted), and any company filtering nuance (the optional company parameter is described in schema but not in description).
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?
The input schema already provides descriptions for all parameters (from_account_ref, to_account_ref, amount, txn_date, private_note, company). The description adds no additional semantic context, achieving the baseline for high schema coverage.
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 the verb 'Create', the resource 'bank transfer', and the context 'between accounts in QuickBooks Online'. It uniquely identifies the tool's purpose among many create_* siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use a transfer versus other payment-related tools (e.g., create_payment, create_bill_payment). No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses the soft-delete behavior (make inactive), which is a key behavioral trait. However, it does not mention any side effects, authorization needs, or rate limits. With no annotations, the description carries the full burden, and this is partial.
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 sentence with no wasted words. It front-loads the core action and context. However, it could arguably include more detail without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple but lacks output schema and annotations. The description does not mention what happens after deletion (e.g., response, success indication). It is incomplete for a tool that modifies data.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds no information about the parameters. Schema coverage is 50% (company is documented, params is not). For a low-coverage schema, the description should compensate, but it does not. The nested idOrEntity parameter is unexplained.
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 the verb 'Delete' and the resource 'employee', and clarifies it's a soft delete (make inactive). It distinguishes itself from other sibling tools like create or update.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. For example, it doesn't mention that updating the employee's status could achieve the same result. A user must infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It only states 'Retrieve,' which implies a read operation, but does not mention any side effects, authorization needs, rate limits, or return characteristics. It adds minimal value beyond the obvious.
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, front-loaded sentence with no unnecessary words. It efficiently communicates the core action and resource, though it could benefit from slight expansion for clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool without an output schema, the description is adequate but incomplete. It does not indicate the return format or that the result is an attachable object. Given the simplicity, it meets the minimum viable standard.
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 coverage is 50%, so the description should compensate. It reinforces the 'id' parameter purpose but does not explain the 'company' parameter's role or default behavior. The description adds only marginal meaning beyond the schema's own parameter descriptions.
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 'Retrieve a specific attachable from QuickBooks Online by ID,' with a specific verb and resource. It distinguishes itself from sibling tools like 'search_attachables' and other 'get_*' tools by focusing on a single entity retrieval by ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no context about the 'company' parameter being optional. It lacks explicit when-to-use and when-not-to-use instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as read-only nature, data freshness, or impact on QuickBooks. It simply states the output, leaving the agent uninformed about side effects or limitations.
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?
The description is a single, well-formed sentence with no redundant information. It is front-loaded and gets straight to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description explains the output (assets, liabilities, equity) but omits important contextual details such as the date range parameter (critical for a balance sheet) and the fact that it is a point-in-time report. No output schema exists, so more context would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With only 50% schema description coverage, the description should fill gaps but does not. It adds no meaning beyond the schema's parameter descriptions; it doesn't explain that start_date and end_date set the report period or how accounting_method affects the report.
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 the tool generates a Balance Sheet report and lists the key accounts (assets, liabilities, equity). This distinguishes it from sibling report tools like get_profit_and_loss or get_cash_flow.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus other report tools. The description does not mention prerequisites, date range considerations, or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but fails to disclose behavioral traits such as idempotency, authentication requirements, or response structure. It merely states the action without any operational context.
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?
The description is a single, front-loaded sentence with no wasted words. It meets the conciseness standard perfectly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get-by-ID tool with two parameters and no output schema, the description is minimal but functional. It covers the essential purpose but lacks details about error handling, return format, or usage notes that would aid an agent unfamiliar with QuickBooks Online.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not explain the parameters beyond implying the 'id' parameter is the bill ID. The 'company' parameter is documented in the schema but not in the description. With 50% schema coverage, the description should compensate but does not.
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 the verb 'Get', the resource 'bill by ID', and the source 'QuickBooks Online'. It effectively distinguishes from sibling tools that target different resources (e.g., get_account, get_bill_payment).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like search_bills for listing bills or create-bill for adding bills. The description lacks any contextual clues about preconditions or intended scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must fully convey behavioral traits. It only states it 'generates a report,' implying a read-only operation, but fails to disclose potential limitations, data freshness, authentication requirements, or whether it affects QuickBooks state.
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?
The description is a single, efficient sentence that communicates the core functionality with no wasted words or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the lack of output schema, the description does not clarify the structure of the report, whether it returns a list with balances per customer or aggregated totals, or what format to expect. More detail is needed for a complete understanding.
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?
The schema provides adequate descriptions for all parameters (report_date, customer, summarize_column_by, company) with 100% coverage. The description adds no additional parameter-specific meaning beyond the schema, meeting the baseline for high coverage.
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 the tool generates a Customer Balance report from QuickBooks Online showing outstanding balances by customer, using a specific verb and resource. It distinguishes itself from sibling financial report tools like get_aged_receivables or get_profit_and_loss.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of preferred scenarios, exclusions, or when a different tool like get_aged_receivables might be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description only states the basic operation. It does not disclose what happens if the ID is not found, authentication needs, rate limits, or any side effects. For a simple read operation, the description adds minimal behavioral context beyond the function name.
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 concise sentence with no extraneous information. However, it may be too brief, lacking details that could be added without significant length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (get by ID), the description is functionally complete for a basic understanding. However, with no output schema or additional context about the deposit structure, and many sibling tools, it could be more informative.
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?
The schema coverage is 50%, with the required 'id' parameter described as 'Deposit ID' and the optional 'company' parameter described. The description does not add any additional meaning beyond the schema; it merely repeats the concept of getting by ID.
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 the action 'Get' and the resource 'a deposit by ID' from QuickBooks Online. It is specific and distinct from sibling tools like search_deposits.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like search_deposits or other get tools. There is no mention of context, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fails to disclose behavioral traits such as return format, error behavior, permissions, or rate limits. It only states the basic function.
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?
The description is a single, efficient sentence that front-loads the core action without any redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is insufficient. It does not indicate what the tool returns, how to interpret results, or how to handle missing IDs.
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?
The input schema already provides descriptions for both parameters (id and company). The description adds no extra meaning beyond what the schema offers.
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 the action (get), the resource (a single sales receipt), and the means (by ID), distinguishing it from related sibling tools like 'search_sales_receipts'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., search_sales_receipts for multiple receipts) or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose any behavioral details beyond the basic read operation implied by 'search'. With no annotations, it should clarify that this is a read-only, non-destructive action, potential authorization requirements, or rate limits. This is insufficient.
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 extremely concise—one sentence—and front-loaded with the essential purpose. However, it could include slightly more detail without becoming verbose, so a 4 rather than 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description should provide more context about what the tool returns or how filtering works. The schema covers parameters, but the description does not synthesize them into usage guidance. It is minimally adequate.
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?
The description does not add meaning beyond the input schema, which already describes each parameter (customer_ref, dates, limit). Schema coverage is 50% (only the top-level params and company are documented), but the description offers no additional insight. Baseline 3 is appropriate.
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 the action ('Search') and resource ('sales receipts') in QuickBooks Online. It distinguishes from sibling tools like 'get_sales_receipt' (single record) and 'create_sales_receipt' (create operation).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'get_sales_receipt' for a single record or other search tools. The description does not mention context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description fails to disclose behavioral traits such as whether only specified fields are updated or all fields are overwritten, authentication needs, or idempotency. Minimal disclosure for a mutation tool.
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?
Single sentence, front-loaded with verb and resource. No wasted words, concise and direct.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks completeness for a mutation tool: no output schema, no description of response or side effects, and limited to only a few updatable fields without explanation. More context needed for correct invocation.
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?
Input schema provides descriptions for all parameters (100% coverage), so description adds no additional meaning. Baseline score of 3 is appropriate as schema carries the burden.
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?
Description clearly states 'Update an existing credit memo', using specific verb and resource. It distinguishes from create, delete, get, and search credit memo tools among siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use vs alternatives. Does not mention prerequisites like existing credit memo or sync token requirement. No when-not-to-use or alternative tool references.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It only states that the tool updates a payment, but it does not mention whether the operation is idempotent, what happens with optimistic locking (sync_token), permissions required, or potential side effects. This is insufficient for understanding the tool's behavior.
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?
The description is a single, clear sentence with no unnecessary words. It is front-loaded and efficient, making it easy for an AI agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is too minimal for a mutation tool with no output schema and no annotations. It does not mention required parameters, return values, error handling, or any constraints. The tool is part of a large set of sibling tools, and more context would be beneficial.
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?
The input schema provides descriptions for each parameter (e.g., 'Payment ID', 'Sync token for optimistic locking'), so the schema already conveys meaning. The tool description adds no additional parameter information beyond the schema. With high schema coverage, a score of 3 is appropriate.
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 the verb 'Update' and the resource 'existing payment' in QuickBooks Online. It distinguishes this tool from sibling tools like create_payment, delete_payment, and get_payment by focusing specifically on updating an existing payment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., when to update vs. create a payment) and lacks prerequisites or context for usage. There is no mention of typical scenarios or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description lacks information on behavior such as error handling (e.g., if ID not found), permissions required, or rate limits. For a read operation, basic transparency is missing.
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?
Single sentence with no redundancy. It is concise but could include more detail without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and minimal annotations. The description covers the basic retrieval purpose but lacks details on return format, error responses, or any behavioral notes. It is adequate for a simple tool but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (only 'company' has a description). The description only mentions 'by Id' without clarifying what the ID represents or where to obtain it. It does not add significant meaning 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?
Description clearly states the tool retrieves a specific bill payment by ID from QuickBooks Online. The verb 'Get' and resource 'bill payment' are precise, and it distinguishes itself from sibling tools like 'search_bill_payments' which search multiple records.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives (e.g., search_bill_payments). The purpose is obvious for retrieving a single record by ID, but the description does not mention prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose read-only nature, error behavior for missing IDs, authentication requirements, or rate limits. The description adds minimal behavioral context beyond the operation.
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?
The description is a single, concise sentence that efficiently communicates the tool's purpose with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get-by-ID tool with no output schema, the description is adequate but lacks details on return format, error handling, or pagination. The context signals indicate low complexity, so a minimum viable score is appropriate.
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?
The schema has two parameters: 'id' (required, no description) and 'company' (optional, described). The description mentions 'by Id' but does not explain the format or constraints for 'id'. With 50% schema description coverage, the description adds some context but not enough to fully compensate.
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 the verb ('Get'), resource ('a customer'), and identifier ('by Id') from QuickBooks Online. This distinguishes it from sibling tools like create_customer, delete_customer, and search_customers.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., search_customers for listing). There is no mention of when not to use it or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It fails to disclose behavioral traits such as read-only nature, required permissions, rate limits, or error handling on missing IDs. The description only states the basic operation.
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, concise sentence with no filler words. However, it is so brief that it sacrifices useful context like parameter details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple getter tool, the description adequately conveys the core function, but lacks details on response structure, error behavior, or prerequisites. Given no output schema, more context would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (only 'company' has a description). The description adds no meaning beyond the schema; it mentions 'by Id' but does not specify the ID format or source. The parameter descriptions themselves are insufficient.
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 the verb 'Get', the resource 'journal entry', the method 'by Id', and the source 'QuickBooks Online'. It distinguishes from sibling tools like search_journal_entries and create_journal_entry.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied (retrieve a specific journal entry by ID), but no explicit guidance on when to use this tool versus alternatives (e.g., search_journal_entries for multiple entries, other get_* tools). No exclusions or prerequisites provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only says 'Get', omitting details like read-only nature, required permissions, error conditions, or rate limits. Minimal behavioral disclosure.
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?
Single sentence, no filler, efficiently communicates the core purpose. Highly concise.
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?
For a simple retrieval tool with no output schema, the description is adequate. However, given the large sibling list, minimal context about when this is preferable to search_accounts would improve completeness.
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 50% (id and company both have descriptions). The tool description adds no further parameter information beyond what is in the schema, so baseline 3 is appropriate.
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 the verb 'Get', resource 'account', and source 'QuickBooks Online'. It distinguishes from sibling tools like search_accounts which would return multiple accounts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as search_accounts. No mention of prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only says 'Get', which implies a read operation, but does not mention permissions, rate limits, or potential side effects. For a simple get, this may be acceptable but insufficient without 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?
The description is a single sentence that conveys the essential information without unnecessary words. It is appropriately front-loaded and concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is too brief for a tool with no output schema. It does not explain what the response contains, error behavior, or how to interpret the result. More context is needed for an agent to use it effectively.
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?
The description adds no additional meaning beyond the input schema. Both parameters (id and company) already have descriptions in the schema. Baseline is 3 due to high schema coverage.
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 the action ('Get') and the resource ('a single purchase order') and specifies the identifier method ('by ID'). This distinguishes it from sibling tools like 'search_purchase_orders' which return multiple results, and from create/update/delete variants.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you have a specific purchase order ID, but does not explicitly state when to use this tool versus alternatives like search_purchase_orders or other get tools. No prerequisites or context for when it's appropriate are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states 'get' which implies a read operation, but does not explicitly confirm read-only nature, side effects, or error behavior. The description adds minimal behavioral context.
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?
The description is a single sentence that is concise and front-loaded. No extraneous information.
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?
For a simple get-by-ID tool, the description is largely complete. However, it lacks an output schema and does not mention return format or error handling. Still, it covers the essential purpose.
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 appears to be 100% based on the provided schema, so the baseline is 3. The description does not add meaning beyond what the schema already provides for the parameters.
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 the action (Get), the resource (refund receipt), the identifier (by ID), and the source (QuickBooks Online). It distinguishes from sibling tools like search_refund_receipts and create_refund_receipt.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives, such as search_refund_receipts for finding receipts. No when-not or prerequisite information is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description only states retrieval, but lacks details on error handling, permissions, or side effects. For a simple read operation, minimal transparency is acceptable but not ideal.
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?
Single sentence, front-loaded with verb and resource. No wasted words.
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?
Adequate for a simple retrieval tool given the schema describes parameters and no output schema is needed. However, could mention response format or prerequisites.
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?
Input schema already describes both parameters (id and company). Description adds no extra semantic value beyond what 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?
Description clearly states the tool retrieves a specific tax rate by ID, distinguishing it from search_tax_rates and other get tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this versus alternative tools like search_tax_rates. Only implies use when ID is known.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It states the tool gets a time activity but does not disclose any behavioral traits such as required permissions, error handling, or rate limits.
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?
The description is a single, front-loaded sentence that conveys the essential purpose without unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get-by-ID tool, the description is minimally adequate, but it lacks information about the return structure, error conditions, and the nature of a time activity, which could be important for agent decision-making.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50%, with the 'id' parameter having a description in the schema. The tool description adds no additional meaning to the parameters beyond what the schema already 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 clearly states 'Get a time activity by ID from QuickBooks Online', specifying the verb, resource, and source system. It differentiates from sibling tools like create_time_activity and search_time_activities by focusing on retrieval by ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when you have the time activity ID, but it does not explicitly state when to use this versus alternative lookup methods like search_time_activities, and provides no exclusionary guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as being read-only or idempotent. This is a basic retrieval operation, but the description fails to state that it does not modify data.
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?
A single sentence that is direct and front-loaded. Every word is necessary, with no redundancy or wasted space.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 2 parameters, no output schema, and no annotations, the description is too minimal. It lacks information about return format, error handling, or any behavioral context, leaving the agent underinformed.
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% (both parameters have descriptions). The description adds no additional context beyond what the schema already provides, meeting the baseline but not exceeding it.
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 the verb (get), resource (transfer), and source (QuickBooks Online). It distinguishes from sibling tools like create_transfer, delete_transfer, and search_transfers by specifying retrieval by ID.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. While it implies use for a single transfer by ID, it does not specify when not to use or compare with search_transfers.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It implies a read-only report generation but does not explicitly state side effects, authorization needs, or rate limits. Basic transparency is present but not detailed.
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?
The description is a single sentence that is front-loaded and concise, with no wasted words. It effectively communicates the core function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequate for a simple read tool but lacks information about return format or structure. Given no output schema, the agent might be uncertain about what the tool returns.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (params object lacks description). The description adds little beyond the tool's purpose; it does not explain that params is a required object containing date, vendor filter, and column summarization. Most parameter meaning is left to 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 it generates a Vendor Balance report from QuickBooks Online, showing outstanding balances by vendor. This distinguishes it from sibling tools like get_aged_payables or get_vendor_expenses, which focus on different aspects.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as get_aged_payables or get_vendor_expenses. The description does not specify prerequisites or context for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It states 'Budget is read-only in the QBO v3 API,' implying a safe read operation, but does not explicitly disclose idempotency, authentication needs, or rate limits. This adds moderate transparency.
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?
The description is two sentences with no wasted words. It front-loads the purpose and efficiently adds structural details about the return type and read-only nature.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately explains the return structure (Budget records with nested BudgetDetail fields). However, it lacks information on pagination, sorting, parameter usage, and other behavioral details, leaving gaps in completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only 'company' has a top-level description). The tool description adds no information about the parameters (params, company, or nested fields like name, active, limit), failing to compensate for the low schema coverage.
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 'Search for budgets in QuickBooks Online' with a specific verb and resource. It distinguishes from sibling search tools by mentioning the return of Budget records with nested BudgetDetail line items, which is unique to budgets.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus other search tools or alternatives. It does not mention any exclusions, prerequisites, or comparison to similar search functions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description does not disclose if the tool is read-only, side effects, authentication needs, or rate limits. For a search tool, readOnlyHint is expected but missing.
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?
Single concise sentence with clear verb and resource, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema or annotations. Lacks details on return format, pagination, or default behavior. For a search tool, more context would be beneficial.
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 coverage is high (all parameters have descriptions), so description adds no extra meaning beyond schema. Baseline 3 is appropriate.
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?
Description clearly states verb 'Search' and resource 'refund receipts in QuickBooks Online', distinguishing it from sibling tools like get_refund_receipt and create_refund_receipt.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives (e.g., get_refund_receipt for single receipt). Context is implied by the search operation but not clarified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility. It mentions 'sparse update' but fails to disclose error handling (e.g., if invoice doesn't exist), authorization requirements, or any side effects. Essential behavioral traits like idempotency or validation are missing, making the tool less predictable for an AI agent.
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?
The description is a single, well-structured sentence that conveys all critical information without any unnecessary words. It is front-loaded with the verb and resource, making it quick to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a sparse update with nested objects and no output schema, the description is too minimal. It does not explain what fields are updatable, how to structure the patch, or what the response contains. An agent would need external knowledge to use the tool correctly.
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?
The description adds some value by noting 'sparse update', which hints at the patch parameter's purpose, but it does not explain the structure of the patch object or how fields should be specified. With only 50% schema coverage (company has a description, params does not), the description partially compensates but leaves key details for the agent to guess.
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 the verb 'Update', the resource 'existing invoice in Quickbooks', and the method 'by ID'. It also specifies 'sparse update', distinguishing it from create_invoice and delete_invoice. This leaves no ambiguity about what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use it (to update an invoice by ID with a sparse update), but it does not explicitly state when not to use it or suggest alternatives among the many sibling tools. There is no comparison to other update tools like update_credit_memo, so an agent might need to infer context from the tool name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses 'sparse update' which is important, but lacks details on error handling, authentication, rate limits, or side effects of updates.
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 concise sentence that front-loads the action and key detail 'sparse update'. However, it could be slightly expanded to cover essential context without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description lacks completeness for a mutation tool. It omits success/error outcomes, required permissions, and response details, making it insufficient for an agent to anticipate full behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only company described). The description does not clarify the format of item_id, the structure of patch, or how 'sparse update' relates to parameters, thus failing to compensate for the schema gaps.
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 the action (update), target (existing item in Quickbooks), method (by ID), and a key behavioral trait (sparse update). It distinguishes from create/delete operations among siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage via 'by ID' and 'sparse update' but provides no explicit guidance on when to use this tool vs alternatives like create_item or delete_item, nor any prerequisites or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only states action without disclosing behavioral traits (e.g., duplicate handling, permissions, side effects).
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?
Single sentence with no wasted words; action and resource upfront.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers basic creation but lacks details on return value, required permissions, or behavior with optional fields. Adequate but not thorough.
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 has high coverage (all parameters described). Description adds value with examples but doesn't explain relationships or non-obvious constraints.
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?
Clear verb 'Create' and resource 'payment term' with examples like 'Net 30', 'Due on Receipt'. Distinct from sibling create tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides examples of when to use (creating standard payment terms), but no guidance on when not to use or alternatives like update_term or search_terms.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only states it generates a report. Lacks disclosure on read-only nature, permissions needed, or whether data is a snapshot. No mention of limitations like pagination or date ranges.
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?
Single sentence with no unnecessary words. Front-loaded with the purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema; description lacks details on return format, pagination, or limitations. For a report with multiple parameters, additional context would improve usability.
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 descriptions cover all parameters (report_date, customer, etc.) but tool description adds no extra meaning. With 50% schema coverage baseline, the description does not compensate.
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 the tool generates an Aged Receivables report from QuickBooks Online, specifying the resource (A/R Aging) and verb (Generate). It distinguishes from siblings like get_aged_payables and get_invoice.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like get_customer_balance or get_customer_sales. Usage is implied but not stated when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the basic action, lacking details on error behavior, permissions, or output format. For a read tool, this is insufficient.
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?
A single sentence of 11 words with no waste. Front-loaded with the verb, concise and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given low complexity, no output schema, and moderate schema coverage, the description is minimal but covers the essential purpose. Could include more detail on return values or prerequisites.
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?
The description adds no parameter details beyond the schema. With 50% schema description coverage, it does not compensate, but the schema already defines the required ID and optional company parameter, making it adequate.
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 the action (Get), resource (single payment), identification method (by ID), and source (QuickBooks Online). This distinguishes it from sibling tools like search_payments and other get tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives. It implicitly requires an ID but offers no when-not-to-use advice, which is adequate but minimal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. However, it only states the basic retrieval action and does not mention any side effects, permissions, or rate limits. For a simple read operation, some transparency is still expected.
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?
The description is a single, clear sentence with no unnecessary words. It is front-loaded with the action and resource.
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?
For a simple get-by-ID tool, the description is adequate. It covers the basic purpose, and the schema documents the parameters. However, it lacks hints about the return format or error handling, which would be useful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has two parameters with descriptions, but the tool description does not add any additional meaning beyond what is already in the schema. Given the reported 50% schema description coverage (though schema appears to have descriptions for both params), the description should compensate but does not.
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 the action ('Retrieve'), resource ('payment term'), and identifier method ('by ID'). It distinguishes this tool from siblings like 'create_term' and 'update_term'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving a specific term by ID, but does not explicitly state when to use this tool versus alternatives like 'search_terms' for broader queries. No exclusions or when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. While 'read' implies non-destructive behavior, the description does not explicitly confirm read-only, auth needs, or other side effects. For a simple read operation, this is minimally adequate.
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, concise sentence that front-loads the purpose. It is appropriately sized for a simple read operation, though it could benefit from a brief usage hint without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (2 parameters, no output schema), the description is minimally adequate. It defines the core action and resource, but lacks detail on return values, what constitutes an 'item', and any prerequisites such as authentication or company context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (only 'company' has a description). The description adds no additional meaning beyond the schema: it mentions 'by its ID' but does not clarify what the item_id format is or how it relates to QuickBooks. The parameter names and schema are straightforward, but the description fails to add value.
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 'Read a single item in QuickBooks Online by its ID.' uses a specific verb ('read') and resource ('item'), clearly indicating a read operation on a single entity. It distinguishes from sibling tools like 'search_items' which list multiple items, and 'create_item' which writes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool over alternatives, nor does it mention prerequisites or exclusions. The context of sibling tools implies that this is for retrieving a known item by ID, but there is no direct guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It only states 'Get a vendor by ID' without mentioning rate limits, authentication requirements, error behavior (e.g., 404 if not found), or idempotency. This is insufficient transparency for a tool with no annotations.
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 sentence of 8 words with no wasted words. It is efficient, though it could be slightly more structured (e.g., listing parameters) given the nested object in the schema. Still, appropriate for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with low complexity (2 params, no output schema), the description is somewhat incomplete. It does not indicate what the response contains (e.g., vendor details like name, address). Since no output schema is provided, the description should offer contextual completeness about return values, but it does not.
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 coverage is 50% (company param described, id inside params not described). The description adds meaning to the id parameter by stating 'by ID', but does not explain the nested params object or the company parameter beyond what the schema already provides. It partially compensates for the coverage gap.
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 the action (Get), resource (vendor), method (by ID), and source (QuickBooks Online). It is specific and distinguishes from sibling tools like search_vendors (which searches) and create-vendor (which creates).
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 clearly implies usage when you have a vendor ID. It does not explicitly exclude alternatives, but for a straightforward read-by-ID tool, this is adequate. Siblings like search_vendors exist for searching, but the description does not need to guide there given the tool's simplicity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full burden for behavioral disclosure. It correctly indicates a read/report operation, but omits details on rate limits, authentication requirements, data freshness, or potential performance implications. The description is not contradictory but lacks depth.
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?
The description is a single, clear sentence with no unnecessary words. It is efficiently front-loaded with the core action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description does not explain the format or content of the report (e.g., whether it returns aggregated totals or individual transactions). The date-range and vendor filtering are implied by parameters but not explicitly stated in the description, leaving some ambiguity for an agent.
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% for parameters (all have descriptions), so baseline is 3. The tool description adds no additional meaning beyond the schema, e.g., explaining how vendor filtering or date parameters affect the report output.
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 the tool generates a Vendor Expenses report from QuickBooks Online, specifying the resource (Vendor Expenses report) and the verb (Generate). It distinguishes this from sibling tools like get_vendor_balance or get_profit_and_loss by focusing on expenses by vendor.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for vendor expense reporting but does not provide explicit guidance on when to use this tool versus alternatives (e.g., get_vendor_balance, get_aged_payables). No when-not-to-use or context for selection is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that deletion makes the entry inactive, which is a key behavioral trait. However, it does not mention permissions, reversibility, or side effects, leaving some transparency gap.
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?
The description is a single, well-formed sentence that communicates the core action and nuance without unnecessary words. It is concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a delete operation with no output schema, the description is minimally adequate. It explains the action and the 'make inactive' nuance, but lacks details on expected input format (especially idOrEntity), return value, and error handling. A bit more context would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 2 parameters with 50% description coverage (company is described, params.idOrEntity is not). The description adds no parameter information, failing to clarify what 'idOrEntity' expects. Schema alone is insufficient for agent understanding.
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 the verb 'Delete (make inactive)' and the resource 'journal entry in QuickBooks Online'. It distinguishes this tool from other delete tools by specifying the resource type, and the parenthetical clarifies the operation's behavioral nuance.
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 implies when to use this tool (to delete a journal entry) and hints that the operation makes it inactive rather than hard-deleting. However, it does not explicitly state when not to use it or provide alternatives (e.g., using update_journal_entry to set an active flag). The context of sibling tools makes the purpose clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does well. It discloses key behaviors: that without base64_content it creates a metadata-only record, and with base64_content it uploads file bytes to the /upload endpoint, including the max decoded size (100 MB) and the requirement for content_type. It does not cover authentication or error states, but the core behavioral difference is well explained.
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?
The description is extremely concise: two sentences that front-load the purpose and immediately explain the two operational modes. Every sentence is informative and necessary, with no redundant or vague wording.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, and the description does not mention what is returned (e.g., attachable ID, success status, error details). Given the moderate complexity (nested parameter, two modes), the missing return value information leaves the agent uncertain about the result. The description is good for understanding how to invoke the tool but incomplete for full context.
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?
The description adds significant value beyond the schema, especially for base64_content (explains the upload trigger and metadata-only mode) and content_type (lists supported MIME types and notes it's required when base64_content is present). It also clarifies that attachable_ref is optional. Schema coverage is 50%, but the description compensates well. The company parameter is not mentioned but its schema description is adequate.
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 the action ('create'), the resource ('attachable' file attachment in QuickBooks Online), and distinguishes two modes (metadata-only vs full upload with base64_content), differentiating it from sibling tools like get_attachable, delete_attachable, search_attachables.
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 explains when to use the tool (to create an attachable) and provides two usage modes based on base64_content. However, it does not explicitly state when not to use it or offer alternatives like using update_attachable for modifications. But the context is clear enough for an agent to infer appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![qbo-mcp-multicompany MCP server](https://glama.ai/mcp/servers/Brax-Tech-Internal/qbo-mcp-multicompany/badges/card.svg)](https://glama.ai/mcp/servers/Brax-Tech-Internal/qbo-mcp-multicompany)

Score Badge

Copy to your README.md:

[![qbo-mcp-multicompany MCP server](https://glama.ai/mcp/servers/Brax-Tech-Internal/qbo-mcp-multicompany/badges/score.svg)](https://glama.ai/mcp/servers/Brax-Tech-Internal/qbo-mcp-multicompany)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Brax-Tech-Internal/qbo-mcp-multicompany'

If you have feedback or need assistance with the MCP directory API, please join our Discord server