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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Read-only link generator with no persistent state modifications or charges.' It adds further useful behavior: automatic resolution of size string to size_index and encoding of coupon/quantity parameters, going beyond what annotations provide.

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 well-organized with clear sections and front-loaded purpose. It is longer than necessary and repeats some details, such as the base-link distinction appearing in both the disambiguation and WHEN NOT sections, but the structure makes the content easy to scan and each section serves a clear 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?

The description covers purpose, disambiguation, usage rules, safety behavior, and parameter constraints comprehensively. The main minor gap is that, with no output schema, it does not explicitly state whether the tool returns a raw URL string, a wrapped object, or any error behavior, though the generated URL format is clearly indicated.

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 baseline is 3. The description adds meaning beyond the schema by explaining how 'size' and 'size_index' relate, noting that a size string can be auto-resolved when no index is provided, and clarifying how the final URL is assembled from parameters.

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 states a specific verb and resource: 'Generate the direct 1-click checkout purchase URL for a specific product handle and size variant index' and provides the exact URL pattern. It clearly distinguishes this tool from general browsing links, making it unambiguous and differentiable 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?

The description has explicit 'WHEN TO USE' and 'WHEN NOT TO USE' sections: it should be used only after the user confirms a size, and must not be used during browsing or when size is ambiguous. It even names the alternative base link (https://s.polopan.com/p/{handle}), giving the agent direct decision criteria.

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 and destructiveHint=false. The description adds valuable context: it states the tool is idempotent, automatically filters out-of-stock items, and enriches results with purchase links. It also provides mandatory agent instructions that disclose how results should be presented, all consistent with annotations. No contradiction.

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 longer than typical but well-structured with clear section headings (PURPOSE, WHEN TO USE, BEHAVIOR, PARAMETERS, MANDATORY AGENT INSTRUCTIONS). It front-loads the core purpose and disambiguation. While the mandatory instructions are somewhat tangential to tool invocation, they are organized and do not bury the essential 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 tool with no output schema, the description fully covers invocation and expected behavior: it explains what is returned (curated looks, enriched with links and policy data), how parameters affect results, and even provides post-return instructions for the agent. Nothing critical is missing for correct usage.

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 baseline is 3. The description adds meaningful elaboration beyond the schema: it explains each parameter's role (e.g., 'age' is the target demographic, 'vendor' is a brand filter) and reiterates defaults and constraints in a user-friendly way. This adds value but not a huge amount given the schema is already descriptive.

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 starts with a clear verb+resource: 'Discover complete curated fashion looks styled for specific occasions.' It lists concrete examples of occasions and explicitly disambiguates from sibling tools 'products.search.text' and 'looks.curation.recommend', making the purpose unmistakable.

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 and WHEN NOT TO USE sections with concrete user intents (e.g., 'What to wear to a summer cocktail party?') and names the exact alternative tools for excluded cases. This leaves no ambiguity about selection.

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?

Beyond the readOnlyHint annotation, the description discloses idempotency, automatic exclusion of out-of-stock items, enrichment with permalinks and policy strings, and mandatory agent presentation rules such as linking shortlists differently before and after size finalization. This is substantial 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 long and repeats the in-stock guarantee and read-only nature, but the section headers and front-loaded summary make it scannable. The mandatory agent instructions justify much of the length.

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 5-parameter tool with no output schema, the description covers invocation modes, pagination, stock filtering, returned link behavior, and agent-facing output presentation. The 'handle ... OR ... occasion' phrasing sufficiently implies that at least one mode is required.

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 schema already documents each parameter. The description adds value by explaining the handle-OR-occasion usage pattern, providing concrete examples like 'Wedding & Reception' and 'solid-linen-shirt', and clarifying gender defaults.

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 and resource: 'Get complete recommended outfits.' It clearly defines the two invocation modes (product handle or occasion+gender) and explicitly disambiguates from 'products.search.alternatives' and 'looks.curation.by_occasion'.

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?

Dedicated 'WHEN TO USE' and 'WHEN NOT TO USE' sections give explicit conditions and name the alternative tools, e.g. 'Do NOT use to find substitute alternatives of the same garment (use products.search.alternatives).' An agent receives unambiguous routing guidance.

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?

Beyond annotations (readOnlyHint=true, destructiveHint=false), the description adds significant behavioral context: it mentions automatic size mapping (e.g., '6' -> EU 39), formatting of negative return days as 'Exchange only |X| days', and the structured JSON response fields (e.g., 'is_in_stock', 'available_sizes'). This goes far beyond the annotations by detailing the tool's internal logic and output format.

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 well-structured with clear section headers, making it easy to scan. However, it is quite lengthy; the 'MANDATORY AGENT INSTRUCTIONS' section could be seen as duplicative of other sections, but it does provide actionable directives that might be considered essential. Overall, it is organized and front-loaded with the core purpose, but could be trimmed slightly for conciseness.

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 a relatively complex tool with three parameters, no output schema, and annotations that only cover read-only behavior, the description is comprehensive. It covers the tool's purpose, usage, behavioral nuances, parameter semantics, and even provides mandatory instructions for the agent. There is no significant missing information that would hinder an agent from selecting and using the tool correctly.

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?

Although the schema already documents all three parameters with 100% coverage, the description adds semantic clarity by explaining the purpose of each parameter in the context of the tool's operation. For example, it clarifies that 'handle' is a unique product identifier, 'desired_size' is to verify against inventory, and 'size_index' is a zero-based index. It also hints at the relationship between 'size_index' and the checkout link structure, enriching understanding 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's purpose: verify real-time stock, pricing, specifications, policies, and size variants for a single product handle. It explicitly distinguishes itself from 'products.items.get_by_handle' (raw catalog retrieval) and 'checkout.links.get_direct_url' (final permalink generation), making its unique role unambiguous.

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 provides explicit 'WHEN TO USE' and 'WHEN NOT TO USE' sections, detailing specific scenarios like verifying stock before presenting a product, generating the specifications table, and checking return policies. It also names alternative tools for searching across multiple products, giving clear exclusion criteria.

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 and destructiveHint=false, and the description reaffirms read-only safety while adding beyond-annotation context: idempotency with no persistent state changes, HTTP 404 behavior for missing handles, and the enrichment of the returned document with verified purchase URLs. Does not contradict the 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?

Well-structured with clear section headers and front-loaded purpose. Slightly verbose: the verified purchase link appears twice (first paragraph and behavior bullet) and the PARAMETERS section duplicates schema content, but every other sentence 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?

For a single-parameter tool with no output schema, the description is comprehensive: it enumerates returned contents (catalog metadata, variants, in-stock sizes, prices, purchase link), covers error behavior (404), states safety profile, and routes to alternatives. An agent has everything needed to call it correctly.

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 fully documents 'handle' with type, minLength, and examples. The description's PARAMETERS & CONSTRAINTS section essentially restates the schema rather than adding new semantic meaning, 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+resource ('Fetch the raw product document and metadata for a single item by unique product handle identifier') and explicitly names the siblings it is distinct from (check_stock, search.text), including what each sibling does instead. An agent can disambiguate without opening any other 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 and WHEN NOT TO USE sections that name the alternative tools and the exact conditions that select them ('use check_stock for live variant inventory... use search.text for general keyword searches'). Nothing is left to inference.

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 readOnlyHint/destructiveHint annotations by disclosing that the tool is idempotent, automatically fetches the source product's primary image embedding, excludes the source product handle from results, and returns clean PoloPan purchase permalinks. This gives the agent a clear behavioral model without needing to infer side effects or output format.

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 longer than average but well-organized with clear headings: PURPOSE & DISAMBIGUATION, WHEN TO USE, WHEN NOT TO USE, BEHAVIOR & SAFETY, and PARAMETERS & CONSTRAINTS. The most important information is front-loaded, and each section earns its place, though the parameter section could be trimmed since it duplicates the schema.

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 has 8 parameters, no output schema, and several sibling tools, the description covers purpose, disambiguation, usage boundaries, behavior, and parameter constraints thoroughly. It also mentions the return value shape (permalinks), though it does not fully describe the complete response structure or error behavior, which would be useful 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?

Schema description coverage is 100%, so the input schema already documents every parameter, its type, default, and constraints. The description's PARAMETERS & CONSTRAINTS section largely restates this information, with only minor additions such as clarifying that page_size is 'before limit filtering' and that page refers to the 'search pool'. This is helpful but mostly redundant with 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 opens with a specific verb and resource: 'Find visual substitute products within a designated price bracket for a given fashion item handle using visual image similarity.' It clearly distinguishes itself from siblings by naming products.search.text, products.search.image_url, products.search.image_upload, and looks.curation.recommend, so an agent can immediately tell what this tool is and is not.

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 explicit 'WHEN TO USE' and 'WHEN NOT TO USE' sections, including concrete examples like 'show cheaper alternatives for this shirt under 1500'. It also names the exact alternative tools to use instead in excluded cases, leaving no ambiguity about tool selection.

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 indicate readOnlyHint=true and destructiveHint=false, and the description adds valuable context beyond that: temporary image upload with automatic expiry, automatic MIME type resolution, and enrichment of results with verified purchase links and stock metadata. It also explains the internal mechanism of querying visual embeddings.

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 longer than average, but it is well-structured with clear headings and front-loaded with the core purpose. The parameter section partially repeats the schema, but the repetition is useful for agents because it provides a single consolidated reference for all 14 parameters.

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 14 parameters, no output schema, and a non-trivial upload mechanism, this description is remarkably complete. It covers purpose, disambiguation, when to use, when not to use, behavioral side effects, return content, and every parameter. The mention of returned fields ('in-stock sizes, pricing, and verified purchase URLs') compensates for the lack 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?

Schema description coverage is 100%, so the schema already documents all parameters. However, the description adds a critical constraint not present in the schema: at least one of 'image_path' or 'image_base64' is required, despite both being marked optional. It also consolidates defaults and enum values in a scannable format.

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 pair: 'Upload a local image file (or base64 string) and search PoloPan catalog products using visual image similarity.' It also explicitly distinguishes this tool from 'products.search.image_url' and 'vision.outfit.detect_pieces', making the tool's unique role immediately clear.

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 dedicated 'WHEN TO USE' and 'WHEN NOT TO USE' sections with explicit alternative tools: use 'products.search.image_url' for public URLs, 'products.search.text' for text-only searches, and 'vision.outfit.detect_pieces' for multi-piece outfit decomposition. This leaves no ambiguity about selection.

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 mark readOnlyHint=true and destructiveHint=false; the description reinforces this and adds process details ('downloads the image, generates visual embeddings, retrieves ranked catalog matches') and output enrichment ('verified PoloPan purchase links and stock metadata'). No contradiction with 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 organized into labeled sections with a front-loaded summary, and the disambiguation/usage sections are highly actionable. Minor redundancy: the parameter list duplicates the input schema, adding length without new 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?

Given 11 parameters, no output schema, and several near-sibling tools, this description is comprehensive: it covers purpose, exclusions, behavior, safety, return contents, and parameter constraints. It even names the exact purchase URL pattern so agents know what result links will look like.

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 input schema already documents all 11 parameters. The description's PARAMETERS & CONSTRAINTS section restates defaults, types, and bounds without adding deeper semantics beyond what the schema provides. Baseline 3 is 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 ('search'), resource ('PoloPan catalog products'), and mechanism ('visual image similarity'), then explicitly disambiguates from products.search.text, products.search.image_upload, and vision.outfit.detect_pieces. An agent can tell it apart from siblings immediately.

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 and WHEN NOT TO USE sections with sibling tool names and conditions: public URL vs local/base64, image URL vs text query, single garment vs multi-piece outfit. No inference is required.

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 readOnlyHint/destructiveHint annotations by stating the tool is read-only and idempotent, and by disclosing enrichment behaviors: sanitizing records, computing in-stock size lists, generating verified permalinks, and adding shipping/return policy strings. It also notes deterministic pagination and filtering, giving the agent a clear behavioral model.

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 well-structured with clear headers, front-loaded purpose, and effective disambiguation, making the length justifiable for a tool with 10 parameters and many siblings. However, the 'PARAMETERS & CONSTRAINTS' section largely duplicates the input schema, and the mandatory agent instructions, while useful, are presentation guidance rather than selection-critical content.

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?

Even without an output schema, the description states exactly what the tool returns: matching products, in-stock sizes, specifications, policies, prices, and verified purchase URLs. It also gives agent-facing instructions for presenting results and handling checkout links, covering the operational context an agent needs beyond the 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 description coverage is 100%, so the schema already documents every parameter thoroughly. The description's parameter section largely repeats schema information, though it adds useful examples and clarifies constraints like sort defaults. This is a solid baseline case where the schema carries the load and the description adds only marginal value.

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 and resource: 'Search PoloPan catalog products using a text keyword query.' It further disambiguates from three sibling tools by naming them and contrasting text search against image search, alternatives, and occasion-look curation. An agent can reliably select this tool based on the stated purpose alone.

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?

Dedicated 'WHEN TO USE' and 'WHEN NOT TO USE' sections give explicit conditions with concrete examples such as 'black leather jacket' and name the exact sibling tools to use instead for image, substitute, or outfit queries. This leaves no ambiguity about when to invoke this tool versus alternatives.

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?

While annotations already declare readOnlyHint and destructiveHint, the description goes further by stating the tool is 'read-only and idempotent' and specifies the input methods (image_path, image_base64, image_url) with the constraint that exactly one must be provided. It also discloses the output structure (label, confidence, box) and the threshold's range, adding valuable context beyond the 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 well-organized with clear sections (PURPOSE, WHEN, BEHAVIOR, PARAMETERS) and avoids redundancy. It is longer than minimal but each sentence serves a purpose, such as disambiguation and usage rules. Slight redundancy exists in the parameter explanations (schema already contains similar), but it remains focused.

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 moderate complexity (4 params, no output schema), the description is exceptionally complete. It covers purpose, disambiguation, usage rules, behavioral details, input constraints, and return format. An agent has everything needed to correctly invoke the tool without additional research.

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 covers all parameters (100% coverage), but the description adds practical context for each, such as example paths, the meaning of threshold, and the exact-one-source constraint. It also clarifies the output format, which is not in the schema, providing extra value for parameter usage.

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 purpose: deconstructing outfit images into individual fashion pieces with bounding boxes and confidence scores. It lists the piece types (e.g., Upper-body garment, Dress, Footwear) and explicitly distinguishes it from sibling tools like products.search.image_url, making its unique role unambiguous.

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 explicit WHEN TO USE and WHEN NOT TO USE sections, detailing scenarios for multi-piece outfit images versus single garments, and contrasts it with text-based search. This directly guides the agent on when to select this tool over alternatives like products.search.image_url or looks.curation.recommend.

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