AsterPay — EUR Settlement for AI Agents

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

Annotations already declare readOnlyHint and idempotentHint, and the description adds value by detailing the return structure (score 0-100, tier, components) and noting it is 'free'. This provides behavioral context beyond the structured annotations, though it does not mention every edge case (e.g., invalid addresses).

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 compact (two sentences) and front-loaded with the acronym and purpose. Every sentence provides essential information: what it does, what it returns, and the input, with no redundancy.

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 read-only tool with one parameter, the description covers input, output, use case, and cost/safety, making it fully self-contained. The absence of an output schema is mitigated because the return values are explicitly described.

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 the single 'address' parameter, and the description merely restates 'Input: an Ethereum address' without adding new meaning. The baseline of 3 is appropriate since the schema fully handles parameter semantics.

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 uses a specific verb ('score') and identifies the resource ('AI agent or wallet'), clearly distinguishing it from sibling tools like market_rates or settlement_estimate. It explicitly states the tool's function: assessing trustworthiness before transactions.

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 phrase 'before paying or transacting with it' provides clear usage context, indicating when this tool is appropriate. However, it does not explicitly contrast with sibling tools or state when not to use it, missing the full 5-point criteria for explicit alternatives.

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?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description's 'read-only' reinforces this, and 'No input' and 'Free' add a little context, but it does not disclose any additional behavioral traits (e.g., staleness of rates, rate limits). Since annotations cover the safety profile, a score of 3 is appropriate—it adds some value but not rich behavioral detail.

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 extremely concise, using three short sentences that each add value: what the tool does, that it requires no input, and its free/read-only nature. No wasted words, and it front-loads the core purpose immediately.

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 no-parameter read-only tool, the description fully covers what the agent needs: it explains what the tool returns (current market rates), provides concrete examples (USDC, EURC, major crypto rates and FX), and clarifies the resource (AsterPay). No output schema is present, but the description adequately conveys the expected return at a high level. The sibling tools are unrelated, so no further context is needed.

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 has zero parameters, and the schema coverage is effectively 100% (empty schema). The description explicitly states 'No input,' which is redundant but harmless. There is no parameter meaning to enhance, and the baseline for 0-parameter tools is 4. The description meets this baseline without needing to compensate.

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 a specific action ('Get current reference market rates') and identifies the resource ('used by AsterPay') with examples of the rates included. This unambiguously distinguishes it from the sibling tools (check_agent_trust, merchant_resolve, settlement_estimate), which serve entirely different purposes.

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 provides clear context that this tool is for retrieving market rates with no input, and it is free and read-only. While it does not explicitly name alternatives or exclusions, the uniqueness of this tool among its siblings makes the intended usage obvious. It lacks an explicit 'when not to use' but still gives sufficient guidance.

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?

The description explicitly states 'Free, read-only — resolution does not move money,' reinforcing the readOnlyHint annotation. It adds context about 'provable sources only' and the demo endpoint, which goes beyond the annotation's raw flags. 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?

Three sentences with no fluff: purpose, parameter requirements, and safety/demo tip. Front-loaded with the main action. Every sentence adds value.

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 covers purpose, parameter usage, and safety. It implies the return is an IBAN/BIC endpoint. It could elaborate on the exact output structure, especially with no output schema, but it's sufficiently complete for an agent to invoke correctly.

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 coverage is 100%, so baseline is 3. The description adds semantic linkage between parameters (EITHER merchant_id OR business_id with business_id_type) and clarifies the 'demo' type value, which is not in the schema. This extra context lifts it above 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 states a specific action ('Resolve a European business to its verified payment endpoint') and clearly names the resource (AsterPay's Merchant Payment Endpoint). This distinguishes it from siblings like check_agent_trust or market_rates, which serve different purposes.

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?

It gives clear usage context: 'Provide EITHER a merchant_id OR a business_id together with its business_id_type' and lists valid types. The demo tip adds practical guidance. It doesn't explicitly state when to avoid this tool, but the parameter combination rules are strong guidance.

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?

Annotations already mark readOnly, and the description reinforces with 'Free, read-only — no payment is made.' It also discloses the fee formula (0.5% + €0.10) and the EU rail detail, adding valuable behavioral context beyond the 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?

Two concise sentences cover purpose, outputs, input, and safety, with no extraneous content. Every sentence earns its place, and the structure is front-loaded with the core action.

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 covers return values (rate, fee, net, timing) and the fee structure, which is critical given no output schema. For a simple one-parameter tool with strong annotations, this is complete and actionable.

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 fully documents the 'amount' parameter with a human-readable format, and the description repeats 'Input: a USDC amount.' With 100% schema coverage, the description adds minimal extra parameter semantics, so the baseline of 3 is appropriate.

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 tool estimates USDC→EUR conversion via AsterPay's EUR off-ramp, with specific outputs (exchange rate, fee, net EUR, SEPA timing). This distinguishes it from siblings like market_rates, which likely provide rates without the settlement fee breakdown.

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 says 'Estimate converting a USDC amount to EUR' and 'Input: a USDC amount,' which clearly indicates when to use it. It does not explicitly name alternatives or exclusions, but the context is unambiguous for settlement estimation.

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