Australian ingredient scanner MCP — 21k+ AU products, 237 chemical rules, 17 condition tags.
Scored across 5 tools
Each tool targets a distinct concern: catalogue stats, magnet guide content, URL templates, barcode scanning, and missing-product submission. The only slight overlap is that get_magnet_samples and get_resources both touch magnet guides, but one returns content while the other returns URL templates.
All tools use lowercase snake_case with a clear verb prefix: get_* for retrieval operations and scan_/submit_ for actions. This creates a predictable and consistent naming pattern with no mixed conventions.
Five tools is well-scoped for a barcode-lookup utility: one core action, one feedback action, and three supporting informational tools. No tool feels redundant, and the set is neither too thin nor too heavy.
The core scan-and-submit workflow is covered, and get_resources supplies canonical URLs for product pages, alternatives, and documentation. Minor gaps remain: there is no direct tool for fetching alternatives or tracking submission status, though these are workable via returned URL templates and the moderation queue.
Return the size of the indexed Australian product catalogue — total, food, beauty, and total scans performed. Useful to set user expectations on coverage.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It describes the output but does not explicitly state read-only nature, authentication needs, or performance characteristics. For a simple stat tool, this is adequate but not rich.
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-load the main action with no wasted words, achieving high efficiency.
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 no parameters, no output schema, and no annotations, the description is sufficient: it explains the tool's purpose and the specific data it returns for the Australian catalogue.
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?
With zero parameters and 100% schema description coverage, the baseline is 3. The description adds value by naming the specific metrics returned, exceeding what the empty schema provides.
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 returns the size of the indexed Australian product catalogue, specifying four metrics (total, food, beauty, scans). This distinguishes it from sibling tools like scan_barcode or submit_missing_product.
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 on when to use ('useful to set user expectations on coverage'), but does not explicitly exclude use cases or compare to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the six condition-specific magnet guides with sample product images. Each guide is a strict-clean shortlist (eczema-safe personal care, clean shampoos AU, mineral-only sunscreens AU, pregnancy-safe beauty, fragrance-free essentials, snacks without artificial dyes).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the tool returns six curated guides with sample images, which is transparent for a non-destructive, read-only operation. No hidden behaviors.
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, front-loads the main action, and uses concise, informative language with no wasted 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?
For a zero-parameter tool with no output schema, the description provides sufficient context about the result set. Minor gap: does not clarify if sample images are real or placeholder, but this is not critical.
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 tool has no parameters, and the schema is empty. The description adds meaning by specifying the exact content of the guides, which goes beyond the schema's null 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 clearly states the tool lists six specific condition-based magnet guides with sample product images, and enumerates the conditions. This distinctively differentiates it from sibling tools like get_catalog_stats or scan_barcode.
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 when condition-specific product recommendations are needed, but does not explicitly state when to use this tool over alternatives or provide exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
URL templates for chained queries — product page, per-product alternatives, category alternatives, magnet guides, OG images, and full LLM-ready documentation. Use to give the user/agent canonical links they can fetch or render directly.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavior. It states it provides URL templates, implying read-only, but does not clarify if data is static or fetched externally. Adequate but not rich.
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 key information. First sentence enumerates output types, second gives usage. No wasted 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?
Tool has no parameters or output schema, so description is the sole source. It explains purpose and usage but does not specify return format (e.g., array of strings, structured object). Adequate for a simple 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?
Input schema is empty (0 parameters), so schema coverage is 100%. Baseline score of 4 applies; description adds no parameter info, which is acceptable.
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?
Description explicitly states the tool provides URL templates for specific purposes (product page, alternatives, guides, etc.). Distinguishes from sibling tools like get_catalog_stats and scan_barcode.
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?
Explicit usage guidance: 'Use to give the user/agent canonical links they can fetch or render directly.' Does not provide when-not-to-use or alternative tools, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Look up an Australian product by barcode (EAN/UPC/JAN, 6–14 digits) and get full chemical-safety analysis. Returns the product info (if found) plus an array of flagged ingredients with severity (red/amber), the matching chemical rule, source citation, and condition-specific notes. Optional conditions array escalates flags for users with chronic conditions: mcas, eczema, pcos, fertility, pregnancy, fibromyalgia, pots, ibs, hashimotos, fragrance, autism, adhd, asthma, autoimmune, endometriosis, lyme, chronic-fatigue.
| Name | Required | Description | Default |
|---|---|---|---|
| barcode | Yes | 6–14 digit barcode (EAN/UPC/JAN). Common: 13-digit EAN. | |
| conditions | No | Optional list of personal condition tags to escalate flags for. Multiple supported. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description explains the tool's behavior thoroughly: it returns product info and flagged ingredients with severity, rule, citation, and notes, and optionally escalates flags based on conditions. It does not mention any side effects or destructive actions, which is appropriate for a read-only lookup. However, without annotations, it could explicitly state it performs no modification.
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 yet comprehensive, front-loading the core purpose and then detailing the output and optional conditions. Every sentence adds value without unnecessary verbosity.
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 no output schema, the description fully explains the return value structure. It covers both parameters, provides examples of conditions, and gives enough context for an agent to use the tool correctly. For a tool with two parameters and no nested objects, this is 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 input schema has 100% coverage, and the description adds significant meaning beyond the schema: it explains that the barcode is for Australian products, that conditions escalate flags, and lists all supported conditions. This provides clear context for both 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 clearly states the tool's purpose: look up an Australian product by barcode and get chemical-safety analysis. It specifies the input format (EAN/UPC/JAN, 6-14 digits) and the output (product info, flagged ingredients with severity, rule, citation, notes). This distinguishes it from siblings like get_catalog_stats or get_resources.
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 implicitly guides usage by detailing the tool's functionality and optional conditions for chronic conditions. However, it does not explicitly state when to use this tool versus alternatives or when not to use it. Given that siblings are unrelated, the lack of direct comparison is acceptable but not optimal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Request that a product be added to the Low Tox Scanner index. Useful when scan_barcode returns product_found: false. Submission goes to a moderation queue.
| Name | Required | Description | Default |
|---|---|---|---|
| brand | No | ||
| notes | No | Freeform context for the moderator | |
| barcode | Yes | 6–14 digit barcode | |
| category | No | ||
| product_name | No | ||
| ingredients_text | No | Comma-separated ingredient list copied from the product packaging |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses that submissions go to a moderation queue (delayed action). Does not mention authentication, rate limits, or outcome clarity. Adequate but not comprehensive.
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 purpose, then context. No wasted words. Efficient and clear.
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 moderate complexity, no output schema, and 6 params, the description covers the essential workflow (trigger after scan failure) and moderation queue. Lacks detail on response or constraints, but sufficient for most agents.
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 50%. The description adds no additional meaning beyond schema. Baseline 3 for medium coverage; no extra value from description.
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 the specific verb 'Request that a product be added' and identifies the resource 'Low Tox Scanner index'. It also provides context linking to scan_barcode and distinguishes from sibling tools like scan_barcode.
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 tells when to use this tool: when scan_barcode returns product_found: false. Mentions submission goes to moderation queue, hinting at non-immediate outcome. Could be more explicit about when not to use or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_catalog_statsget_magnet_samplesget_resourcesscan_barcodesubmit_missing_productOpen Beauty Facts MCP — Open Beauty Facts API (free, no auth, keyless).
Can this person eat this? Allergens, additives and nutrition from a barcode.
Unlock the power of food transparency with our Open Food Facts MCP server. Easily look up any food
Nutrition MCP — wraps Open Food Facts API (free, no auth)
Add one secure layer between your agents and this server.
