ComplianceCN — toys, batteries, cosmetics, food contact: CE, GPSR, UN 38.3, CPC/GCC and more

Structured product readiness check

preflight_product

Read-onlyIdempotent

Single-call readiness check when you already have structured product facts: category, markets and any evidence held. Returns the applicable requirements, an evidence checklist and the gaps in one response, with no follow-up needed. For a plain-language description instead, use market_access_check, which also returns preliminary requirements on its first call and continues into evidence assessment and an optional human-reviewed pack.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`case_id`	No	The case this call continues, from an earlier result. Omit to start a new product case.
`markets`	No	Optional destination-market hints. Omit when product_description names the destination.
`category`	No	Optional structured category hint. Canonical IDs and common English/Chinese labels are accepted. Omit when product_description contains enough information for extraction.
`language`	No	Language for seller-facing text. Questions and messages come back in it; en or zh.	zh
`age_group`	No	Intended user age. Decides whether toy safety rules apply and which small-parts and warning duties follow.
`food_type`	No	The food the product will contact. Simulant selection for migration testing depends on it.
`has_radio`	No	Whether the product transmits: Bluetooth, Wi-Fi, NFC, or any other radio. Decides the RED conformity route in the EU and FCC authorisation in the US.
`has_battery`	No	Whether the product contains or ships with any battery, including a coin cell in a remote.
`battery_type`	No	Cell chemistry. Decides whether UN 38.3 transport testing and battery-passport duties apply. Use unknown rather than guessing.
`is_sunscreen`	No	Whether the product is sold as sun protection. Sunscreens carry separate testing and labelling duties.
`product_name`	No	Human-readable product or SKU name
`repeated_use`	No	Whether the article is single-use or reused. Repeated use requires migration testing across successive cycles.
`evidence_held`	No	Evidence IDs the seller already holds, from a previous result's evidence_checklist. Marks each item held rather than unknown; it does not verify the document.
`evidence_text`	No	Document/evidence information already known or extracted by an agent. File upload is optional and separate. Do not paste sensitive certificates or full reports into agent chat.
`sales_channel`	No	Where the product is sold. Marketplaces impose their own evidence requests on top of the legal requirements.
`verified_only`	No	Exclude decision rules not checked against primary sources
`eu_destination`	No	Destination member state, where it changes the answer. Language and producer-registration duties differ across the EU.
`evidence_notes`	No	Document and evidence information known by the seller or agent: filenames, supplier claims, models, standards, issuers, dates, or extracted key text. Explicit evidence may be mapped to evidence IDs; authenticity, completeness and SKU coverage still need original-file and human review.
`contact_duration`	No	How long the product touches food in normal use. Long-term contact triggers stricter migration testing.
`supply_chain_role`	No	The seller's role in the chain. Decides which duties are theirs rather than the manufacturer's or importer's.
`applicable_modules`	No	Optional additional modules that should be assessed together with the primary category, for example toys plus battery-electronics.
`claims_therapeutic`	No	Whether the product claims to treat, prevent or cure anything. A therapeutic claim moves a cosmetic into a different regime.
`contact_temperature`	No	The temperature at contact. Hot fill and cooking raise migration limits and change the test.
`product_description`	No	Preferred first input: describe the product, destination market, sales channel and any known supplier documents in plain language. The tool extracts a preliminary profile and fills the internal checklist. Required when category/markets are not already supplied.
`sells_in_california`	No	Whether the product is sold into California. Proposition 65 warning duties apply on top of federal requirements.
`clarification_answer`	No	Continuation shortcut for the exact same case_id when answering questions_required. Send the seller's natural-language answer here; the service restores and merges the previous canonical product profile. Never use this field to introduce a different product or SKU.
`ingredients_reviewed`	No	Whether the full ingredient list has already been checked against restricted-substance annexes.
`is_childrens_product`	No	Whether the product is marketed as a children's product; keep unknown when not established.
`evidence_observations`	No	Sanitised document observations that may continue between workflow stages: apparent type, filename/reference, models, organisation, date, identifiers, standards, confidence and unresolved issues. Do not include file contents, verbatim extracts, quotations, addresses or unrelated personal information.
`food_contact_material`	No	The material that touches food. Migration limits and test methods differ by material.
`accessible_small_parts`	No	Whether a child could reach a part that fits in a small-parts cylinder, including parts freed by reasonably foreseeable use.
`includes_mains_charger`	No	Whether a mains plug, wall charger or power adapter ships in the box. A supplied charger is separately in scope.
`is_electrically_operated`	No	Whether the toy is electrically operated, including mains-powered or battery-powered operation.
`evidence_inventory_complete`	No	True only when evidence_notes/evidence_text and evidence_held together form a complete inventory. Otherwise unprovided applicable evidence remains unknown, not missing.
`battery_compartment_security`	No	How the battery compartment is secured. Button and coin cells carry stricter duties because ingestion is the hazard.
`toy_chemical_assessment_complete`	No	Whether a chemical safety assessment covering migration limits has already been completed for this toy.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	Yes
`payload`	Yes

TDQS

A4.7/5.0

Behavior4/5

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

Annotations indicate read-only, idempotent, and non-destructive behavior, which the description does not contradict. Beyond annotations, the description discloses that the tool returns requirements, evidence checklist, and gaps in one response with no follow-up needed, which is useful. It also implies it does not verify evidence (via schema description for evidence_held). However, it doesn't mention potential limitations like the need for human review for evidence authenticity, but that is covered in parameter descriptions. Slight bonus for adding the 'no follow-up needed' behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the purpose and key benefits, then immediately naming the alternative with specific differentiators. Every word earns its place, no fluff. It is concise yet comprehensive, covering purpose, usage, and alternative routing in a compact form.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (36 parameters, multiple legal domains, output schema present), the description is remarkably complete. It covers what the tool does, when to use it, what it returns, and how it differs from the primary sibling. The rich schema descriptions handle parameter details, and annotations cover safety profile. Nothing essential is missing for an agent to decide whether to call this tool and how to structure the call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds minimal parameter-level semantics, but the schema descriptions are already rich. The description implies the use of structured facts, which aligns with parameters like category, markets, and evidence_held. It also contrasts with market_access_check for plain-language input, reinforcing that structured parameters are expected. The description does not need to repeat schema detail, so a 4 is justified for adding some contextual guidance (structured vs. plain-language).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: a single-call readiness check for structured product facts, returning applicable requirements, evidence checklist, and gaps. It names the specific inputs (category, markets, evidence) and contrasts with sibling market_access_check, which handles plain-language description and further steps. This distinguishes it effectively from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says to use this tool when you 'already have structured product facts' and to use market_access_check for plain-language descriptions, which also continues into evidence assessment and human review. This provides clear when-to-use and when-not-to-use guidance, and names the alternative. It also highlights the single-call nature, making the usage context unambiguous.

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

All ComplianceCN — toys, batteries, cosmetics, food contact: CE, GPSR, UN 38.3, CPC/GCC and more tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0

Disambiguation4/5

The check_* tools each target a distinct regulatory aspect (transport, EU DoC, labeling, marketplace, US certification), and the auxiliary tools (describe, explain, compare, watch) are clearly separate. The only potential confusion is between market_access_check and preflight_product, which both assess product requirements but differ in input style and follow-up workflow.

Naming Consistency4/5

Most tools follow a verb_noun pattern (check_battery..., compare_market..., explain_claim), but market_access_check reverses the expected 'check_market_access' order and preflight_product uses a less common verb. Still, the pattern is recognizable and mostly consistent.

Tool Count5/5

Eleven tools is well within the ideal range for a compliance-checks server. Each tool addresses a distinct user scenario (general assessment, specialized checks, comparison, coverage, claims, alerts), and none feels redundant or superficial.

Completeness4/5

The server covers the core assessment lifecycle: initial check, structured preflight, detailed specialist checks, cross-market comparison, claim explanation, and regulatory change alerts. Minor gaps exist, such as no way to cancel alert subscriptions or retrieve a saved full report, but the main compliance-checking domain is thoroughly covered.

Resources

Need Help?