ShipRate AU

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 the central behavior: carriers bill on the greater of actual vs cubic weight, and the tool returns the cubic weight under each convention plus the charged weight. It lacks explicit statement of side effects (none) or precision/rounding behavior, but for a stateless calculation this is close to complete.

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 tight sentences: rationale, then inputs and returns, then the pre-quoting usage rule. The opening motivation sentence is slightly ahead of the core action, but every sentence earns its place 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?

There is no output schema, and the description compensates by describing the return values (cubic weight under each common convention and the weight actually charged). For a four-parameter, side-effect-free computation, 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 coverage is 100%, so the four inputs (length/width/height in cm, weight in kg) are already fully documented in the schema. The description adds only the framing that dimensions and actual weight together determine the result, not new per-parameter meaning, so the schema-does-the-work 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?

The description names a specific computation (cubic/volumetric weight and chargeable weight from dimensions and scale weight) and explains the domain rule behind it, so an agent can distinguish it instantly from the quote_* and lookup siblings. The title reinforces rather than merely restates the name.

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 says to use it before quoting so the weight passed to a quote tool matches what will be billed, which is clear routing guidance relative to quote_domestic_au and quote_international_from_au. It does not state any when-not-to-use case, but for a pure calculation tool the context is unambiguous.

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 useful work: it discloses that the value set is fixed rather than free text, and that plausible-looking values such as 'general' or 'others' are rejected. It stops short of saying how the list is returned or whether it is cached, but the core behavioral trait (closed enumeration, invalid input fails) is clearly disclosed.

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, each adding something: what is returned, how the values behave, and when to call. The 'fixed list, not free text' constraint is front-loaded before the failure examples, so the most decision-relevant fact lands first.

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?

No output schema exists, so the description must imply the return shape; 'Returns the exact goods categories' reasonably communicates a list of accepted category strings. It could be slightly more explicit about the returned format, but for a zero-parameter enumeration tool with no side effects, nothing essential 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; no parameter text is needed or expected here.

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 ('Returns the exact goods categories') and pins down the scope: those accepted by the commercial rate source. This is unmistakably distinct from the sibling quote/weight/postcode tools, which compute values rather than enumerate the accepted vocabulary.

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?

Gives concrete trigger conditions — call it after a quote returned a category error, or before quoting to pick the closest match. It does not name any alternative tool or state when not to call it, but for a fixed-list utility there is no real alternative to route to.

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 burden and does disclose the key behavioral trait: the tool is bidirectional and can return plural suburbs plus state. It does not say what happens on an unknown postcode/suburb or how multiple matches are ordered, which is a modest gap for a low-risk read lookup.

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 core capability and then the use cases; nothing is padded. 'Works in both directions' is mildly redundant with the bidirectional phrasing in the first sentence.

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?

No output schema exists, so the description must cover return values; it partially does by naming suburbs and state. It leaves open error/empty-match behavior and ordering of multiple matches, but for a simple two-parameter lookup this is close to 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 description coverage is 100%, so both parameters are already documented in the schema, including the state code list and examples. The description adds only the rationale for supplying state (ambiguity across states), which the schema also states, so baseline 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 precise verb (Resolve) and resource (Australian postcode/suburb) and explicitly covers both directions of the mapping, so an agent knows exactly what it gets back. It is clearly distinct from the sibling quoting and weight-calculation tools.

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?

Gives concrete when-to-use contexts: validating an address before quoting, and disambiguating a suburb name that exists in several states. No explicit when-not or named alternative tool is given, but the usage conditions are specific and actionable.

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 exist, so the description carries the full burden and does well: it names both data sources (AusPost retail PAC and Easyship's commercial panel), the return contents (price, currency, transit time), sorting (cheapest first), and a caveat that the two sources are not directly comparable. Auth, rate limits, and error behavior remain undisclosed, keeping it from a 5.

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?

Front-loads the core capability before the usage sentence, and each sentence contributes (sources, return shape, sorting caveat, when to use). Slightly dense but no wasted 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?

With no output schema, the description usefully explains the return structure and a comparability caveat; with no annotations, it discloses the dual-source behavior. Parameters are fully covered by the schema. Mostly complete, though mutation/auth/rate-limit context is absent (not applicable to a read-only quote, so minor).

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 8 parameters (defaults, ranges, enums, examples). The description only alludes to 'weight and route'; it adds no syntax or format detail beyond the structured fields, making the baseline 3 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+resource (live shipping prices for a domestic Australian parcel) and adds distinguishing scope: 'WITHIN Australia', 'two independent sources at once'. This clearly separates it from the sibling quote_international_from_au without opening the 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?

Provides explicit when-to-use: 'asked what it costs to send a parcel between Australian postcodes, or which courier is cheapest for a given weight and route.' It does not name alternatives or state exclusions (e.g., when to reach for quote_international_from_au), so it stops short of 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 burden and does well: it discloses the two quoting sources, that AusPost pricing is retail-only, that destination duty/tax is excluded and paid by the recipient, and that results come back per service with price and currency. Missing only auth/rate-limit or failure-mode 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?

Four sentences, each carrying distinct information: capability, source split, usage trigger, and the pricing caveat. Front-loaded and free of repetition, though slightly dense.

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 9-parameter tool with no annotations and no output schema, the description covers the important gaps: what is returned (per-service price and currency) and the retail/duty caveat. It could say more about which source wins when both quote, but it is largely complete.

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 every parameter (HS code, category enum list, weight cap, postcode roles) is already documented. The description adds no parameter-level detail beyond the schema, so the baseline 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 — live shipping quotes for a parcel sent FROM Australia overseas — and names both price sources (AusPost retail PAC and Easyship commercial panel). This clearly separates it from the domestic sibling quote_domestic_au.

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?

Gives an explicit trigger: 'Use when asked what it costs to post something overseas from Australia.' The direction (FROM Australia) implicitly excludes inbound/domestic quoting, but no sibling is named as the alternative for those cases.

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