Agent Credit Bureau

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

Beyond the annotations, it discloses genuinely useful behavior: the tool is paid (charges the published USDC price once per unique payment authorization) and returns evidence comparability, coverage, and unknowns rather than a score. This explains the cost and non-read-only nature, though the destructiveHint is not spelled out (e.g., what funds are consumed).

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, front-loaded with the core comparison and followed by the output boundary and cost model. Every sentence carries information, though the cost sentence could be tightened.

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 paid, open-world tool with a nested input schema and no output schema, the description covers the output nature and cost well. It omits any explanation of the nested exposure object's fields, which is the largest remaining gap for correct invocation.

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 0% across two required params with nested objects, so the description must compensate. It does loosely map the params (subject = the AI/software agent, proposed_exposure = the credit/deferred-payment exposure), but it never explains the nested Asset, principal, duration, secured, or obligation_type fields, so coverage remains partial.

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 (Compare) and a well-defined resource (attributable economic history vs. a proposed credit/deferred-payment exposure), so the agent knows exactly what the tool does. It does not explicitly differentiate itself from the sibling get_agent_credit_report, so it stops short of a 5.

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 clarifies the output boundary ('never a lending recommendation or credit score'), which implies this is a due-diligence/evidence tool rather than a scoring tool. However, it gives no explicit when-to-use guidance or a direct comparison against get_agent_credit_report, leaving the choice between siblings to inference.

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=false, destructiveHint=true, openWorldHint=true and idempotentHint=false. The description adds genuinely new behavioral context beyond those hints: it is a 'paid tool' (cost/payment requirement) and delivers historical evidence only. It does not explain the payment mechanism, auth needs, or what the destructive/paid side effect actually is, and its 'Retrieve' framing sits in tension with the destructiveHint annotation without resolving it.

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 compact sentences with no filler; the response payload is front-loaded and the clarifying 'not a lending decision' qualifier follows. The eight-item enumeration is dense but each item maps to real returned evidence, so it earns its place.

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?

With no output schema, the description usefully enumerates what the report contains, and annotations cover the safety profile. Missing for a paid, non-idempotent tool: the meaning/format of the single id parameter, cost/price of the call, and any guidance on repeated calls, leaving it only adequate.

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?

There is a single required parameter 'id' with 0% schema description coverage, so the description carries the full burden — and it does not compensate. It only implies the id identifies an 'economic agent on Base', giving no format, expected value type (address? id?), or examples.

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?

States a specific verb (Retrieve) and a concrete resource set — observed economic obligations, principal-time exposure, settlement actors, counterparty relationships, coverage and unknowns — for an economic agent on Base. It implicitly carves out its role ('returns historical evidence, not a lending decision') against the sibling, but never names assess_agent_credit_exposure, so differentiation must be inferred.

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 clause 'returns historical evidence, not a lending decision' hints at when this is appropriate vs. the assessment sibling, and 'paid tool' signals cost. However, there is no explicit when-to-use/when-not statement, no named alternative, and no prerequisites — usage is only implied.

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