dopamine - the shop AI agents can buy from

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

With no annotations provided, the description fully discloses the tool's non-real nature ('no payment', 'just a joke') and its key output (returns an order id). It also hints at the absurd delivery behavior of the follow-up tool, adding valuable context beyond the schema.

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 concise sentences, front-loaded with the critical fake nature, then the return value, then the next step. 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?

For a simple joke tool with no annotations and no output schema, the description covers the essential behavior, return value, and follow-up step. It is complete enough for an agent to invoke the tool correctly and understand the expected result.

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 description does not elaborate on the parameters beyond what the schema already provides. product_id is self-evident from the tool name 'buy', and address already has a descriptive schema comment. The description adds no additional semantic depth to the parameters, and with 50% schema coverage, it fails to compensate for the undocumented product_id.

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 that the tool simulates a purchase (with quotes around 'Buy'), returns an order ID, and is distinct from sibling tools like get_product, search_products, and track_order. It uses a specific verb and resource, and explicitly positions itself as the fake purchase step.

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 instructs to call track_order afterward, providing a clear sequential usage pattern. It also states the tool is '100% fake, no payment' and 'Nothing real happens,' which implicitly excludes real-world purchasing and sets expectations for when to use it.

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 of disclosing behavior. It conveys that this is a read operation, but it does not explain error handling, authentication requirements, or the exact return structure. The 'from search_products' constraint adds some 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?

The description is a single, focused sentence with the action and resource front-loaded, containing no extraneous words.

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?

Despite lacking an output schema, the tool is simple with one parameter, and the description provides the essential context (source of the id). The absence of return type details is a minor gap; overall, it is complete enough for a get-by-id tool.

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 sole parameter 'id' gains meaning from the description: 'from search_products' indicates the id must originate from that tool, which is valuable beyond the bare schema. It doesn't provide format examples, so not a 5, but it compensates for the 0% schema coverage.

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 ('Get') and resource ('product') with a qualifier ('by id'), clearly distinguishing it from siblings like search_products (which lists) and buy (which purchases).

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 parenthetical '(from search_products)' implies the tool is intended as a follow-up to search_products, providing contextual usage guidance. However, it does not explicitly state when not to use it or mention alternative tools.

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 adds context that the catalog is a parody and products are fake, which is important for setting expectations. However, without annotations, it does not mention other behavior such as read-only nature, result limits, or any side effects, leaving gaps.

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 a compact two-sentence text that immediately conveys the action and output with no unnecessary words. It is well-structured and 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?

Given the tool's simplicity, the description covers the core search function but misses important details such as category usage and any usage notes. With no annotations or output schema, the description is only minimally complete for making an informed decision.

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 a description for 'query' but not for 'category', despite it being an enum. The tool description does not explain how category should be used, leaving the filter parameter ambiguous. Thus, the description adds no meaningful parameter semantics beyond 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 searches the dopamine catalog and returns fake products. This distinguishes it from siblings like buy, get_product, and track_order with a specific verb and resource.

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 guidance on when to use this tool versus alternatives. The description does not mention that search_products is appropriate for discovering products before buying, nor does it exclude using it for other purposes.

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 discloses that the order is simulated, that the timeline is accelerated (~2 min), and that repeated calls are needed. It also mentions the possible outcome of being 'eaten by a whale,' adding non-obvious behavioral information.

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 sentence states the core purpose, and the second provides essential usage and behavioral context. Every word 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?

While the description covers the workflow and polling behavior, it does not describe the return value or output shape, and there is no output schema to fill that gap. For an agent invoking the tool, knowing what to expect in the response is important, so this is a notable omission.

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 description only says 'by id,' which maps to the order_id parameter but adds no extra meaning regarding format, source, or how to obtain the ID. Given 0% schema description coverage, it fails to compensate for the lack of parameter detail.

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 'track' with a resource 'a fake order by id'. It clearly distinguishes from sibling tools like buy, get_product, and search_products by focusing on post-purchase tracking.

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 clear context that the order journey runs on a fast clock and advises calling multiple times to watch it progress. Although it doesn't explicitly mention when not to use it or alternatives, the usage pattern is clear from the context.

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