BAM Kaarsen catalog

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 communicates that the result is a navigation tree containing scents, product types, and collections with ids, and the action 'browse' implies a read-only lookup. It does not fully specify tree shape or pagination, but that is minor for this simple catalog browse operation.

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 tightly written sentence defines the resource, its content, its ids, and the downstream integration with list_products. There is no filler and all context 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 tool with only one optional parameter and no returned output schema, the description is sufficient. It tells the agent what the response contains and how to use it for list_products, leaving little to inference.

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 lang parameter has 100% schema coverage with an enum and default, so the schema already fully explains the input meaning. The description adds no parameter-specific details, which is acceptable because the schema owns that responsibility.

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—the catalog navigation tree—and enumerates its contents: scents, product types, collections, and their ids. It also differentiates the tool by framing it as a taxonomy source for list_products, which clearly separates it from sibling product-lookup 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?

'for use with list_products' gives clear context on the intended workflow: browse the catalog to obtain ids, then pass those ids into list_products. It provides useful guidance without explicitly listing exclusions for search_products or get_product.

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 is transparent about what the tool returns, listing all data fields. Since it is a 'get' operation, it is implicitly read-only, but this is not explicitly stated. The absence of annotations means the description carries the burden, but the verb 'get' and the listing of details make the behavior clear enough.

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, concise sentence that effectively communicates the scope and contents of the response. It uses a clear structure, listing the included attributes without unnecessary detail, making it easy to parse.

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 simplicity of the tool (two parameters, no output schema), the description is sufficiently complete: it covers what the tool returns and the purpose of each parameter. It does not mention error handling or edge cases, but these are not critical for a simple get operation. The absence of output schema means the description must imply the return format, which it does through the list of fields.

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?

Both parameters have descriptions: lang explains the language and default value ('default en'), and bam_id specifies it is the product id from search or listing results. These add semantic value beyond the schema, clarifying the meaning and origin of the inputs, exceeding the baseline for full 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 clearly states that the tool returns 'full details for one product', specifying the exact items included (description, price, EAN, stock, categories, URLs). The title 'Get product details' reinforces the action. It is distinct from sibling tools that list or search products, focusing on a single product's complete information.

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 that this tool is for retrieving a single product's full details, but it does not explicitly state when to use it over alternatives like search_products or list_products. It lacks explicit guidance on use cases (e.g., 'Use this when you have a specific product ID and need comprehensive information').

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 behavioral disclosure. It adds the 'exactly one facet id' constraint and the 'visible catalog' scope, which are helpful, but it omits other behaviors like pagination, sorting, or error handling. It adds some context but not rich detail.

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-loads the purpose, and delivers the key filtering rule with zero waste. 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?

Core behavior is covered (optional filter, full catalog when no filter), but without an output schema, the description should explain what is returned (e.g., fields, pagination, ordering). That is missing, making it incomplete for a list tool with no 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?

Schema coverage is only 25% (only lang has a description). The description compensates by explaining that scent_id, collection_id, and product_type_id are facet ids that can be used (at most one) and come from browse_catalog. This adds meaning beyond the schema, even though it doesn't individually describe each id parameter.

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?

Clearly states it lists catalog products and describes the optional facet filter, referencing browse_catalog as the source of facet ids. It distinguishes from get_product (single item) and search_products (search) by focusing on listing with a specific filter style, though it doesn't explicitly name those alternatives.

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 usage: without a filter you get the whole visible catalog, and you can filter by exactly one facet id from browse_catalog. This suggests when to use it (full listing) and that browse_catalog provides the filter values, but it doesn't explicitly contrast with search_products or give conditions for choosing this over other 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?

No annotations are provided, so the description must disclose behavioral traits. It does not mention whether the operation is read-only, whether it involves side effects, or any rate limits, pagination, or return format. As a search tool, it is presumably safe, but the description leaves these assumptions implicit rather than explicit.

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 concise—two sentences—with the core functionality stated first and additional details (matching fields, all-words requirement) following succinctly. Every sentence earns its place with no redundancy or 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 does not describe what the tool returns (e.g., product results, count, order). Since this is a search tool, an agent needs to know the response shape to use it effectively. The description is adequate for triggering a search but incomplete for understanding the full interaction.

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 covers both parameters (query and lang) with descriptions, but the description adds meaningful context: it specifies what fields are searched (product names, descriptions, and EAN barcodes) and that multiple words must all match. This goes beyond the schema's basic parameter definitions, enhancing an agent's understanding of query behavior.

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's function: it performs a fuzzy keyword search over the candle catalog, matching names, descriptions, and EAN barcodes. This distinguishes it from sibling tools like browse_catalog or list_products, which imply browsing or listing rather than searching. However, it does not explicitly name a sibling or contrast itself, so it falls short of a 5.

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 the tool is for keyword-based searching, but it does not explicitly state when to use it over browse_catalog or list_products. There is no guidance on exclusions or alternatives. The usage context is somewhat implied by the word 'search' but lacks direct comparison to siblings.

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