Retrieve current IRS high-low method per diem rates for any US location to support accountable-plan travel reimbursement (Revenue Procedure 2019-48). Classifies each location as High-Cost or Low-Cost with separate lodging and meals-and-incidentals (M&IE) components. Premium API. Cost: $0.25 USDC via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| lookup | Yes | Full street address, ZIP code, city, county, or state (CONUS) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate destructiveHint=true, and the description reinforces this by stating 'Premium API. Cost: $0.25 USDC via x402', disclosing the financial cost. The description also adds behavioral info about classifying locations as High-Cost/Low-Cost with separate components. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences plus a cost line, all front-loaded. The first sentence states the action and resource, the second adds classification details, and the third notes pricing. Every sentence earns its place with no extraneous text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple one-parameter input and no output schema, the description adequately conveys the tool's behavior and output (classification with lodging and M&IE components). However, it does not detail exact return fields or error handling, which could be beneficial for a paid API.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of the single parameter with a description. The tool description repeats that the lookup can be a full address, ZIP, city, county, or state (CONUS), adding little beyond the schema. However, the schema description already provides the same information, so there is no extra value, meeting the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Retrieve' and the resource 'IRS high-low method per diem rates for any US location', and specifies the purpose 'to support accountable-plan travel reimbursement (Revenue Procedure 2019-48)'. It also distinguishes from siblings by describing the unique classification into High-Cost/Low-Cost with lodging and M&IE components, which no other tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use this tool: for retrieving IRS per diem rates for US locations for travel reimbursement. It cites the specific revenue procedure, providing clear context. However, it does not explicitly mention when not to use this tool or list alternatives among siblings, but given the niche functionality, this is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct data operations (matching, standardization, enrichment) with clear descriptions. Minor overlaps exist, e.g., address_match_advanced vs global_address_match, but descriptions differentiate them.
All tools follow a consistent 'interzoid_descriptive_function' pattern in snake_case, making it easy to predict purpose from the name.
58 tools is high for a single server, exceeding the typical 3-15 range. While each serves a specific data enrichment function, the quantity may overwhelm agents without clear categorization.
The tool surface covers a broad domain including address, company, person, and financial data. Minor gaps exist (e.g., no reverse IP lookup, limited social media coverage), but core data needs are well-addressed.
