catalog

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

With no annotations, the description carries the full burden. It honestly discloses the scope boundary — what fields are included and explicitly what data categories are absent — which is the most important behavioral trait. However, it does not disclose the output format, how loose name matching behaves, or what happens when a card is not found, leaving gaps for a tool with zero annotation support.

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 with zero filler. The primary purpose is front-loaded in the first sentence, and the second sentence earns its place by setting explicit scope boundaries. Every clause contributes to correct tool selection.

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 one-parameter tool, the description is nearly complete: it states the operation, the cardinality, the fields compared, and the exclusions. The main gap is that no output schema exists and the return format is not described, but the implied side-by-side catalog-record output is reasonably inferable from the description and tool name.

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% (card_names with minItems/maxItems and 'matched loosely' is fully documented in the schema). The description's '2-5 cards' reinforces the schema bounds but adds no new meaning beyond what the input schema already provides, so the baseline of 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?

States a specific verb and resource ('same catalog record for 2-5 cards at once') with an explicit field scope ('comparing fees, networks and which benefits each carries'). The exclusion list ('no earning rates, welcome-offer amounts, transfer ratios, or bonus sizes') sharply differentiates it from siblings like estimate_point_value and find_transfer_routes.

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?

Provides an explicit when-to-use condition (2-5 cards needing comparison of fees/networks/benefits) and an explicit when-not-to-use via the exclusion list, which implicitly routes the agent to sibling tools for earning rates, transfer ratios, and bonus sizes. It stops short of naming the alternatives directly, so it doesn't earn a 5.

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 well: it discloses that these are Miles' personal estimates, not market prices, that they must be attributed, and that the tool intentionally avoids other card-related data. This is meaningful behavioral context.

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 deliver the core definition, usage pattern, and important caveats with no wasted words. The essential information 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 simple read-only estimation tool with two optional parameters, the description fully covers what the tool returns, how to invoke it, important attribution caveats, and what it deliberately excludes.

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 the baseline is 3. The description adds value by explaining the no-arguments list behavior and emphasizing exact program spelling from that list, which supplements the loose matching note in the schema.

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 ('estimate'), resource ('loyalty point's value in cents'), and optional multiplication by balance. It also differentiates from card-fact and transfer tools by explicitly excluding earning rates, welcome offers, transfer ratios, and bonus sizes.

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?

Clear guidance is provided: call with no arguments to list all programs and exact spellings, and omit program to list all. It also tells users what this tool is not for, though it does not explicitly name sibling tools as 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?

No annotations are provided, so the description carries the behavioral burden. It does disclose an important limitation: no ratios, bonus sizes, expiry dates, or route-valuation guidance. It also states that the route graph only shows existence and bonus running status. However, it doesn't say what the actual output looks like (since there is no output schema), nor mention that to_program is loosely matched while from_program has strict enum values, which is relevant behavioral nuance.

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 dense sentences, front-loaded with the main capability and then negative scope limitations. Every clause earns its place; the text is compact but informative. No fluff.

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 read-only search tool with fully documented parameters, the description is nearly complete. The main gap is the absence of output-shape information, but since there is no output schema anywhere, even a brief note on what a route row looks like would help. Also, despite having 5 parameters and 1 enum, the description gives enough guidance for an agent to call it correctly. The lack of an output schema makes this less complete than a tool with a rich output schema, but it is still strong.

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 already explains all 5 parameters with 100% coverage, so the baseline is 3. The description adds value beyond the schema by clarifying that the route graph does not include transfer ratios or bonus sizes, which prevents an agent from misinterpreting a route result as a recommendation. It also reinforces that calling with neither argument lists every source, which is not stated in the schema. This pushes it to a 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 description names the exact resource (route graph of loyalty currency/program transfers) and the key actions it supports: finding where a currency transfers, what reaches a destination, and whether a bonus is running. It also explicitly distinguishes itself from card-facts sibling tools by saying 'Card facts only — no earning rates, welcome-offer amounts, transfer ratios, or bonus sizes.' This makes the tool's purpose unmistakable.

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 strong context for when to use the tool: when you need routes, not ratios or bonus sizes. It does not name alternative sibling tools like estimate_point_value or compare_card_facts explicitly, but it clearly says what the tool does NOT cover, which effectively steers an agent away from using it for those questions. Slightly missing an explicit 'use X instead' statement for those cases.

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 disclose important behavior: 'Card name is matched loosely,' the exact field categories, and what is deliberately omitted. It does not describe no-match or ambiguous-match behavior, but for a simple lookup this is solid disclosure.

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 and front-loaded: one sentence scopes and lists the fields, and a short second sentence states exclusions. Every clause adds useful information with no filler.

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 one-parameter lookup with no output schema, the description is nearly complete: it lists the returned facts, explains matching behavior, and clarifies limitations. A small gap is that it does not say what happens when no card matches or when a loose match is ambiguous.

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 the baseline is 3. The description adds meaning beyond the schema by explicitly stating that card_name is matched loosely, telling the agent that exact naming is not required.

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 identifies a precise resource (one card's catalog record) and enumerates the exact facts returned, including issuer, annual fee, network, and foreign transaction fee. It also lists exclusions, clearly distinguishing it from sibling tools like estimate_point_value and find_transfer_routes.

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 provides clear context for when to use the tool: when a single card's catalog facts are needed. It explicitly states exclusions (no earning rates, welcome-offer amounts, transfer ratios, or bonus sizes), but it does not name the specific sibling tools to use instead.

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 behavioral burden. It discloses that results are short rows, only includes card facts, and limits results to cards open to new applicants. It does not explain how filters interact or matching behavior, but the core behavioral boundaries are clear.

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 with no filler. The first sentence states the tool's purpose and main filter axes; the second sentence points to the sibling tool and sets data-boundary expectations.

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 10-parameter search tool with no annotations and no output schema, the description explains what is returned, what is excluded, and where to get fuller data. It leaves some ambiguity about exact return fields and filter combination, but not enough to prevent correct selection and 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 100%, so the schema already documents all 10 parameters. The description broadly repeats the filter categories but adds no new meaning beyond what the schema provides, keeping this at the 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 uses a specific verb and resource: 'Find credit cards open to new applicants,' and lists concrete filter dimensions such as issuer, annual fee, network, and benefits. It also distinguishes itself from get_card_facts by noting it returns a short row rather than a full record.

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 explicitly tells the agent to 'call get_card_facts for one card's full record,' which names the alternative and the condition for using it. It also states what this tool will not provide — earning rates, welcome-offer amounts, transfer ratios, and bonus sizes — helping route the agent elsewhere.

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