get_priceGet the price quote in euro cents for sending a fax. Pricing: 5.00 EUR for up to 5 pages, plus 0.50 EUR per extra page, plus VAT based on the payer's billing country (0% VAT outside the EU).
| Name | Required | Description | Default |
|---|---|---|---|
| page_count | Yes | Number of pages in the PDF | |
| billing_country | Yes | ISO 3166-1 alpha-2 country code of the payer (e.g. DE, FR, NL) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description fully discloses the pricing behavior: 5.00 EUR for up to 5 pages, 0.50 EUR per extra page, and VAT handling based on billing country. This goes beyond the readOnlyHint annotation, which only indicates no destructive side effects, by explaining exactly how the quote is computed.
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 a single sentence plus the pricing breakdown, with no unnecessary words. It is front-loaded with the core purpose and efficiently conveys all critical information.
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?
The description explains the pricing logic well but does not specify the return format (e.g., whether it returns just a number or an object with breakdown). Given no output schema, a slight improvement would be to state the response structure explicitly.
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?
Though the schema already describes both parameters, the description adds meaning by explaining how page_count and billing_country are used in the pricing formula. This transforms abstract parameters into a concrete business rule, significantly enhancing an agent's understanding.
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 'Get the price quote in euro cents for sending a fax', specifying both the verb and the resource. The detailed pricing formula distinguishes it from sibling tools like send_fax, making the tool's role unambiguous.
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 implies the tool should be used before sending a fax to estimate cost, but does not explicitly state when to use it over alternatives or mention contexts where it's not appropriate. Sibling tool names provide additional context but could be clearer.
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.
Each tool has a clearly distinct purpose: checking balance, getting fax status, pricing, and sending. No overlap.
All tool names follow a consistent verb_noun pattern: check_balance, get_fax_status, get_price, send_fax.
Four tools is appropriate for a focused fax service, covering the essential operations without unnecessary clutter.
Core workflow (price, send, status, balance) is covered. Missing cancellation or listing tools, but these are not essential for the primary use case.