cashbackpro

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

Beyond the annotations (readOnly, idempotent), the description reveals the exact calculation logic, the tier percentages, and that it returns a result for every level. This adds meaningful behavioral context about what the tool does and doesn't do, including no external lookups.

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 two sentences, tightly packed with necessary information: the formula, the level shares, and the pure-calculation nature. No fluff or redundancy.

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 calculation tool with no output schema, the description is sufficient. It fully explains the inputs, the calculation, and the output behavior (per level). It doesn't describe the exact return format, but that's not essential for a pure math tool with clear annotations.

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 baseline is 3. The description adds value by explaining how the parameters relate (price × commission rate) and how the result varies by CashbackPro level, which goes beyond the simple field descriptions 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 clearly states the tool calculates cashback on a purchase, using a specific formula and level-based shares. It distinguishes itself from sibling tools like get_cashback_link or get_product_details by emphasizing it's a pure calculation, not a lookup.

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 explicitly says 'Pure calculation — nothing is looked up,' which implies when to use it (for estimation without needing live data) and when not to use it (when live product/link data is needed). It doesn't name sibling alternatives explicitly but provides enough context to differentiate.

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 description goes well beyond the annotations by explaining the affiliate-link mechanics, the effect of a connected CashbackPro account on commission, the requirement of an Authorization Bearer token, and that the response indicates which case applies plus the disclosure text. This richly discloses behavior without contradicting any annotations.

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 two sentences with no fluff, though the second sentence is long and packs in a URL and multiple conditions. It is efficient and front-loaded with the primary purpose.

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?

Given the simple single-parameter schema and presence of annotations, the description adequately explains the affiliate context and what the response includes (which case applies, disclosure text). It does not detail response structure, but that is not required in the absence of an output schema.

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 schema already provides 100% coverage with a description for the only parameter 'product' (AliExpress product URL or numeric product ID). The tool description adds no additional parameter meaning, 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?

The description opens with a specific verb+resource: 'Return the CashbackPro purchase link for an AliExpress product.' This clearly distinguishes the tool from its siblings (calculate_cashback, get_promo_codes, etc.) by stating exactly what it produces and for what domain.

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 implies when to use it (when a purchase link is needed) but does not explicitly state when to use it versus alternatives or provide exclusions. No alternatives are mentioned, so guidance is left to inference from the tool name and purpose.

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 read-only, idempotent, and non-destructive behavior, so the description doesn't need to restate that. It adds a small amount of context (e.g., 'authoritative' implies a trusted data source, and the listed fields hint at return behavior), but it does not disclose additional operational traits like data freshness, latency, or error handling. With strong annotations, this is sufficient.

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?

A single, tightly written sentence front-loads the action ('Look up one AliExpress product by its numeric ID') and follows with a compact list of outputs. There is no repetition, filler, or extraneous detail; every word contributes meaning.

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 tool with no output schema, the description adequately covers the input format, the tool's scope, and the full set of returned values. It doesn't address error cases or unavailability, but the simplicity and the provided annotations make this sufficiently 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?

The schema provides full 100% coverage of the single parameter with a clear description ('Numeric AliExpress product ID') and a regex pattern. The description merely restates 'numeric ID' without adding new format or value semantics, so it relies on the schema and earns the baseline 3.

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 ('Look up') with a clear object ('one AliExpress product by its numeric ID') and enumerates all the details returned (price, rating, sales volume, commission rate, category, cashback levels). This clearly distinguishes it from siblings like search_products, which would be used for discovery, and calculate_cashback, which focuses solely on cashback math.

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 phrase 'by its numeric ID' establishes a clear context: use this when you have a specific product ID and need authoritative details. It does not explicitly name alternative tools or state when not to use it, so it falls short of the explicit/exclusive guidance that would 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?

Annotations already declare read-only and idempotent. The description adds valuable behavior: expired codes excluded, daily refresh, and cashback stacking. This goes beyond the annotations without contradicting them, though it does not cover every possible detail (e.g., pagination or exact formatting).

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 main purpose, followed by useful boundaries and relationship to cashback. Every sentence earns its place with no redundancy.

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, no-output-schema tool, the description is complete: it covers what is returned (codes, min spend, qty, expiry), scope (USD site), refresh cadence, exclusions, and stacking behavior. It leaves no significant ambiguity.

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 are zero parameters and the schema is empty, so the description does not need to explain parameters. Per the rubric, baseline is 4 in this case, and the description adds no param-specific info but doesn't need to.

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 (list) and clearly identifies the resource (active AliExpress promo codes on the global USD site), including types (platform-wide and product-specific) and key attributes (minimum spend, remaining quantity, expiry). This distinguishes it from siblings like get_cashback_link and search_products.

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 gives clear context: active codes, expired excluded, daily refresh, and stacking with cashback. This implies when to use it, but it does not explicitly state when not to use it or name alternative tools, so it falls 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?

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds two meaningful behavioral details beyond that: automatic filtering of low-quality listings (blocked categories, minimum price) and the conversion of product URLs to CashbackPro affiliate links. This is valuable context without contradicting annotations.

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 primary purpose. The first sentence describes the search and output fields; the second covers filtering and affiliate links. Every clause earns its place with no fluff or repetition.

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 search tool with no output schema, the description does an excellent job: it specifies the return card contents, the filtering behavior, and the affiliate link transformation. It lacks explicit edge-case handling (e.g., no results, pagination) but those are minor given the limit parameter and openWorldHint annotation.

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 (query, limit, max_price_usd) is already documented. The description does not add parameter-specific semantics beyond what the schema provides, so it neither enhances nor degrades the baseline. The mention of 'minimum price' in filtering is a behavior, not a parameter explanation.

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 clearly states the tool searches the AliExpress catalogue and returns product cards with specific fields (price, rating, sales volume, commission rate). This distinct verb+resource combination separates it from sibling tools like get_cashback_link or get_promo_codes.

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 implies this is the entry point for product discovery—the output fields are framed as needed to judge costs—but it never explicitly says when to use this instead of get_product_details or calculate_cashback. No alternatives are mentioned, so guidance is merely contextual.

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