SmartRetry Payment Tools

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

Annotations already declare readOnly, idempotent, non-destructive and open-world behavior, so the safety profile is covered. The description adds genuinely new context: the accepted input span (6 to 8 digits) and an explicit prohibition on submitting full PANs, which is a privacy/security constraint not present in structured fields. It omits data source, freshness, and rate-limit behavior.

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 short sentences, front-loaded with the identity of the tool and its return values, followed by usage and then the critical input constraint. No filler or repetition beyond the necessary safety reiteration.

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 compensates by listing the returned fields explicitly, and it covers the input constraint, the safety rule, and the use case. For a single-parameter lookup tool, nothing an agent needs to call it correctly is missing.

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% and the single parameter already documents 'first 6 to 8 digits, digits only, never a full card number', so the description largely restates the schema. Baseline 3 is the right ceiling here — no additional format, example, or edge-case meaning is contributed.

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?

Names a specific verb and resource ('BIN / IIN lookup') and enumerates exactly what is returned: card network, card type, card level, issuing bank and country. The scope is precise, but it does not explicitly distinguish itself from the sibling lookup_issuer, which overlaps on 'issuing bank and country', so an agent has to infer the boundary.

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?

'Use it to identify a card or where it was issued' gives a clear usage context, and 'Never pass a full card number' is a hard, actionable constraint. It stops short of naming alternatives (e.g. lookup_issuer or lookup_mcc) or stating when-not to use this tool, so it stops at 4.

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 annotations already establish read-only, idempotent, open-world, non-destructive behavior, so the bar is lower. The description adds meaningful context: inputs may be numeric codes, symbolic names, or free-form messages from multiple networks and processors, which signals tolerant cross-provider matching. It does not say what happens when nothing matches or how many results may come back.

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 sentences, front-loaded with the purpose and followed by input scope and the optional provider filter. Every sentence carries information; nothing is redundant within the description itself.

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 two-parameter lookup with no output schema, the description covers purpose, accepted input variety, and provider scoping well. The main remaining gap is the expected return content and behavior on ambiguous or unmatched codes, which an agent would benefit from knowing before calling.

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%, so the schema already documents both parameters, including the same examples. The description reinforces that `provider` is optional narrowing, but adds no format, precedence, or normalization detail beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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 gives a specific verb and resource: explaining why a card payment was declined or failed. It also names the accepted input families and a representative set of networks and processors, which makes it clearly distinguishable from the sibling lookups (BIN, issuer, MCC). It does not explicitly reference those siblings, which keeps it just 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 context of use (a card payment was declined or failed) is implied by the first sentence, but there is no explicit when-to-use framing, no exclusions, and no stated alternative for cases where the code is unknown or the payment succeeded. The agent can infer the trigger, but the description does not guide choice.

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 cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description's main contribution is the fuzzy-match behavior: it accepts partial or misspelled names, which tells the agent it need not have an exact legal name. It also discloses the shape of the result (country, website, phone), which annotations do not.

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 sentences, no filler: the first defines the lookup and its return fields, the second gives the use cases. The most decision-relevant information (what it finds, what it returns) is front-loaded.

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 single-parameter, read-only lookup with no output schema, the description covers what is searched, how tolerant the matching is, what fields come back, and when to reach for it. Nothing an agent needs in order to call it correctly is missing.

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% and the schema already documents the name parameter with examples, so the baseline would be 3. The description adds a genuinely new semantic detail not in the schema: misspelled names are tolerated, which changes how the agent should construct the query rather than retrying with exact spellings.

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 gives a specific verb and resource ("Find card issuing banks by name") and immediately enumerates the returned fields (country, website, phone number). The sibling tools (lookup_bin, lookup_decline_code, lookup_mcc) each target a different lookup domain, so an agent can distinguish this one without opening any schema.

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 states two concrete use cases: confirming the bank behind a card and finding issuer contact details. It does not explicitly name when not to use it or point to a sibling (e.g., use lookup_bin when you only have the first digits), but the intended context is clear enough for correct selection.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered. The description adds genuine value by enumerating what the response contains (category group, high-risk flag, Visa and Mastercard definitions), which is the main thing annotations cannot convey. It does not say what happens when no match is found or how ambiguous business descriptions are handled.

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 sentences, zero filler, and the dual mode is front-loaded right after the tool's name so the agent learns the branching behavior before any detail. Examples are embedded inline rather than padding out extra sentences.

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 carries the return-value burden and does so by naming the four result components. It is slightly incomplete on edge cases — no-match behavior, whether a business description can return multiple candidates, or output format — but for a single-parameter read-only lookup it is nearly sufficient.

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% and already documents the single query parameter, so the baseline is 3. The description earns an extra point by explaining that the one field is polymorphic — it carries either a code or a natural-language business type — and pairs each form with the shape of result it produces, which the schema alone does not make explicit.

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 and resource ("Merchant category code (MCC) lookup") and immediately distinguishes its two operating modes: resolve a code to a definition, or map a business description to a code. Against siblings like lookup_bin and lookup_issuer, the resource is 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?

Tells the agent exactly which input shapes to use and when, with concrete examples ("5411", "grocery store", "software"). It stops short of naming alternatives or exclusions (e.g., when to prefer lookup_bin for card-prefix questions), so the routing guidance is clear but not complete.

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