Subpay Invoice Reader

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

No annotations are provided, so the description carries the burden. It adds one genuinely useful behavioral fact – the service is 'Free' – and enumerates the topics covered, but says nothing about auth requirements, rate limits, or what the response looks like. For a harmless zero-parameter read tool the risk is low, so this is modest but not empty.

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?

A single compact fragment with the key fact ('Free') front-loaded and no wasted words. It is efficient, though the telegraphic style borders on under-specification rather than tight prose.

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?

For a simple informational tool with no output schema and no parameters, listing the covered topics (what extract_invoice reads, arithmetic checks, price, payment networks, terms) is reasonably complete. But it never states that this is the service-documentation endpoint or how the information is returned, leaving a small gap.

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 tool takes zero parameters and the schema is fully described (empty object), so there is no parameter semantics to explain. The baseline for a parameterless tool is 4.

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 title 'About this service' plus the content list make it inferable that this returns service/product information (what extract_invoice reads, checks, pricing, networks, terms). However the description itself never states a verb or the purpose explicitly – it opens with 'Free.' and reads as a bullet list, so an agent must infer the intent.

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?

There is no statement of when to call this tool versus extract_invoice, no prerequisites, and no indication of sequence (e.g. 'call before extract_invoice to learn pricing'). The only implicit cue is that it is a zero-argument informational tool.

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

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

With no annotations, the description carries the full burden and does much of it: it discloses the pricing model ($0.04/page in USDC via x402), that the quote comes before payment, that failed reads are free, and page/size limits. It also explains the null semantics of the checks ('null when the figures aren't printed'). It does not cover latency, retry behavior, or rate limits, which keeps it from a 5.

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?

Front-loaded and information-dense, but it repeats the field list twice (the opening extraction inventory and the 'Returns vendor, customer, invoice number...' sentence), which is partially redundant. The pricing sentence is valuable, but a tighter single field list would have earned the same meaning in fewer words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must describe the return contract, and it does so thoroughly: extracted fields, the arithmetic checks, the passed true/false values, and the null case. Combined with the cost and input constraints, an agent has everything needed to call and interpret it.

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

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

Schema description coverage is 100% for both parameters, so the schema already documents 'document' (base64 PDF, data: URL prefix, ~3 MB/25 pages) and 'fileName'. The description restates the PDF/page constraints but adds no parameter-level syntax or format detail beyond the schema. Baseline 3 applies.

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 states a specific verb and resource ('Reads invoices, bills and receipts from PDF into structured JSON') and then enumerates the extracted fields and the added arithmetic-validation behavior. It is unambiguous what the tool does; the only sibling ('about') is not a competing extraction tool, so no differentiation is required.

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?

Usage context is implied by scope ('PDF', 'max about 3 MB and 25 pages', per-page pricing) but there is no explicit when-to-use, when-not-to-use, or named alternative. An agent can infer applicability from the input constraints, but nothing routes it or sets prerequisites beyond that.

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