Tolstoy Shopper

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

Annotations already indicate readOnly, idempotent, and non-destructive. The description adds rich behavioral detail by enumerating the full set of returned data (description, price, media, videos, size guide, per-variant stock, buy links) and noting the response includes the product image, which goes beyond what annotations state.

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 tight paragraphs, front-loaded with the core purpose and followed by usage guidance and output specifics. Every sentence provides value without 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?

Given the tool's simplicity (one parameter, no output schema), the description is fully complete. It covers what the tool returns, how to use it, where the parameter comes from, and the downstream action (build_cart). Annotations cover safety, leaving no gaps.

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 productRef with a basic description, but the tool description enhances it by explaining that productRef comes from search_products or browse_products and is used to identify the product. This adds meaningful context beyond the schema's one-line definition.

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 'Load full details for one product by its productRef', using a specific verb and resource. It clearly distinguishes this tool from siblings search_products and try_on by focusing on retrieving detailed product information for a single item.

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?

Explicitly instructs when to use: 'Use it to resolve the exact variantId the shopper wants before calling build_cart, and to answer fit/sizing questions from the size guide.' It also indicates the productRef comes from search_products or browse_products, providing clear context and sequencing.

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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful context about marketplace mode (searches across every brand store without store selection) and the productRef relationship to get_product. No contradictions.

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 compact and well-structured: first paragraph introduces the core action, second paragraph gives usage guidance and result handling. No filler or redundant information.

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 read-only search tool with 4 parameters and no output schema, the description covers the essential context: when to use, what the query means, how filters work, and how to follow up via get_product. It is complete for an AI agent to select and invoke the tool effectively.

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 descriptions cover most parameters (75%), so the baseline is 3. The description adds meaning by elaborating on the query parameter with examples and explaining that filters narrow results for a single brand. This enhances the schema's basic descriptions.

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 catalog by a specific free-text query, with examples of query types. It distinguishes itself from browse_products (open-ended browsing) and get_product (full details via productRef).

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?

Explicitly states when to use: 'only when the shopper names something specific to look for.' It also names the alternative for other cases: 'For open-ended browsing, featured, best sellers, or a collection, use browse_products instead.'

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 positive safety annotations (all false), the description carries the burden. It adds context about the interactive photo upload and availability limitation, but it doesn't disclose potential side effects (e.g., whether it changes any state) or describe what happens after the interactive session. The lack of explicit side-effect disclosure leaves some ambiguity.

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. The first clearly states the core functionality, and the second adds the availability caveat and fallback. No filler or unnecessary 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?

The description covers the essential context: what it does, how to get the input, availability constraints, and a fallback path. It doesn't describe the return value format, but for an interactive tool with no output schema, this may be acceptable. The description is fairly complete for a simple one-parameter 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?

Schema description coverage is 100%: productRef is already described as 'Product reference token from search_products.' The description repeats this source information but adds no new parameter meaning beyond what the schema already provides. Baseline 3 applies 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?

The description clearly states a specific action ('Opens an interactive virtual try-on') with a specific resource ('a product by productRef'). It also distinguishes itself from sibling tools by focusing on try-on functionality and referencing search_products for the product reference.

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 indicates when to use the tool (shopper wants virtual try-on) and provides a clear prerequisite (get productRef from search_products). It also notes an exclusions when the brand hasn't enabled try-on and offers an alternative ('viewed via its store link'), though it doesn't explicitly name a sibling tool as the alternative.

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