ChargeGuard Dispute Assistant

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

With no annotations, the description carries the full burden. It does disclose the shape of the data (windows broken down by five named gateways and three card networks), which tells the agent this is static reference content rather than per-merchant data. It says nothing about freshness (whether it reflects current network rules), jurisdiction variance, or return format.

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?

One sentence, no filler, dimensions front-loaded. It is a fragment rather than a complete sentence, so the operation is left implicit, but nothing is wasted.

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 zero-parameter reference tool with no output schema and no annotations, the description covers what the data is keyed by but not what a record contains (e.g., number of days, whether values are calendar or business days). That omission matters for a deadline lookup, where the unit and format are the whole point.

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, so the schema imposes no semantic burden and the baseline is 4. The description's enumeration of gateways and networks is the relevant scoping information and is communicated.

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 a specific resource (chargeback response windows) and its granularity (per gateway, per card network), which clearly separates it from the reason-code siblings. It is a noun phrase rather than a verb phrase, so it never states the operation (retrieve/list), but the get_ prefix and the enumerated dimensions leave little ambiguity.

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 explicit when-to-use statement, no prerequisites, and no mention of the sibling tools. An agent must infer from the name alone that this is a passive reference lookup rather than part of an active chargeback workflow.

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 must carry behavioral weight, and it discloses the fixed size of the result set (9 codes), the covered networks, and the shape of each entry (a one-line summary). It does not discuss permission needs or any dynamic behavior, but for a static, parameterless reference list there is little further behavior to disclose.

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 enumeration scope is front-loaded and the usage cue follows. Every clause adds information an agent can act on.

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 parameterless reference list with no output schema, the description conveys enough about the return content (9 entries, one-line summaries, three networks) to call the tool and interpret results. A note on what a caller should do with the output (e.g. feed a code into lookup_reason_code) would close the remaining 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, which is the baseline-4 case under the rubric. The description's mention of the three covered networks also clarifies that no filtering argument is needed or accepted.

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?

Specific verb (List) plus a precisely scoped resource: the 9 card-network chargeback reason codes, naming the networks (Visa, Mastercard, Amex) and the return format (one-line summaries). That scope makes it clearly distinct from lookup_reason_code, which returns a single code.

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 first when the user mentions a chargeback without a code" gives an explicit triggering condition and implicitly defines when not to use it (code already known). It never names lookup_reason_code as the alternative, so the routing is inferred rather than stated.

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; it does disclose the payload contents (meaning, evidence, window, URL), which is real value. It omits behavioral edge cases that matter here — whether a slug fragment can match multiple codes, what happens on a miss, and whether the lookup is cached/rate-limited. 'Look up' implies a safe read but that is never confirmed.

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, and the return contents are front-loaded before the input forms. Every clause 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?

For a one-parameter read-only lookup with no output schema, the description is close to sufficient because it enumerates the returned fields. The remaining gap is ambiguity handling for fuzzy slug fragments and a nudge toward list_reason_codes for browsing.

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 single parameter already documents both accepted forms with identical examples ('13.2', 'visa-13-2'). The description restates the schema's examples rather than adding new meaning (e.g., normalization rules, partial-match behavior), so the baseline 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?

States a specific verb (look up) and a precisely scoped resource (one card-network chargeback reason code), then enumerates exactly what comes back: meaning, winning evidence, response window, guide URL. The singular 'one' implicitly separates it from the sibling list_reason_codes, so an agent can pick it without opening either 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?

Usage context is only implied: 'one' code suggests a targeted lookup versus the sibling list_reason_codes, but the description never says when to use this instead of listing or get_response_deadlines. No prerequisites or exclusions are stated, leaving the agent to infer routing.

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. It does disclose the key side effect (an email report is sent), that the audit is free, and that it is a third-party ChargeGuard service — genuinely useful context. It does not say what happens on failure, whether repeated submissions are allowed or throttled, or that merchant contact data leaves the system.

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 waste, and the core action and its effect are front-loaded ahead of the prerequisite details.

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 five-parameter mutation with no annotations and no output schema, the description covers the essentials: what happens, what it costs, and what is required. Only minor gaps remain around response shape and confirmation behavior, which are less critical for a one-shot submission.

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 mentions the store URL and contact email but stays silent on the third required parameter (company), as well as platform and notes, adding no meaning beyond what the well-described schema already provides.

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?

"Submit a free ChargeGuard store audit" gives a specific verb plus resource and immediately says what the audit does (reviews payment setup and dispute risk) and what it produces (an emailed written report). It is clearly distinguishable from the read-only lookup siblings, though it does not name them explicitly.

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 is only implied: an agent can infer this is the tool to use when a merchant wants a proactive risk assessment, and "free" plus "requires store URL and contact email" sets a precondition. There is no explicit when-to-use/when-not statement and no guidance on when to prefer a reason-code lookup instead.

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