E-commerce margin calculator: GO/RISKY/NO-GO verdict for Amazon, Etsy, eBay, Shopify, TikTok Shop.
Scored across 2 tools
calculate_margin handles a single product/channel calculation while compare_channels explicitly does cross-channel comparison, so the split is understandable. There is some latent overlap since a margin question could plausibly route to either, but the descriptions give enough guidance to pick correctly.
Both tools follow the exact same snake_case verb_noun pattern (calculate_margin, compare_channels). No mixing of conventions or vague standalone verbs.
Two tools is thin for an e-commerce profitability domain; the server is a focused calculator, so it isn't absurd, but there's little surface area and no room for adjacent operations like batch analysis or target-margin reverse pricing.
Core workflows (single-channel margin verdict plus multi-channel comparison) are covered, but notable gaps remain: no batch/multi-product evaluation, no direct 'price from target margin' input, and comparison is limited to a fixed channel set in one country. Agents can work around these but will hit limits.
Manifeste e-commerce margin calculator. From a selling price and a delivered cost, returns a GO / RISKY / NO-GO verdict, what the seller really keeps per sale after VAT, platform fees (TikTok Shop, Amazon, Etsy, eBay, own store/Shopify), affiliate commission, payment fees, returns and social contributions, plus the levers to reach GO (minimum price, maximum cost), break-even ROAS, maximum ad cost per sale, sales needed per month and points to check. Use it whenever someone asks if a product is profitable, what margin or fees they will have, or how to price it.
| Name | Required | Description | Default |
|---|---|---|---|
| cost | Yes | Delivered cost per unit: product + packaging + shipping to the customer. | |
| price | Yes | Selling price paid by the customer, tax included (e.g. 24.90). | |
| channel | No | Where it is sold: tiktok (TikTok Shop), amazon, etsy, ebay, boutique (own store, e.g. Shopify), physique (in person), autre (other). | |
| country | No | Store country: FR, BE, DE, ES, IT, IE, UE (other EU), UK, US, XX (other). Sets currency, VAT and default fees. | |
| language | No | Language of the answer (default en). | |
| ships_from | No | Where parcels ship from (matters for TikTok Shop in the EU). | |
| vat_percent | No | VAT rate % (default: standard rate of the country; 0 for VAT exemption). | |
| delivery_days | No | Business days from order to delivery (optional, used for the verdict). | |
| stock_quantity | No | Units in the first stock order (default 50). | |
| returns_percent | No | Returns provision % (default 5). | |
| samples_percent | No | Free samples as % of units sold. | |
| ad_cost_per_sale | No | Average ad spend per sale. | |
| discount_percent | No | Promotion % off the price. | |
| shipping_charged | No | Shipping paid by the customer, if any. | |
| fixed_fee_per_order | No | Override the fixed fee per order. | |
| monthly_fixed_costs | No | Monthly fixed costs (tools, subscriptions). | |
| monthly_profit_goal | No | Monthly net profit goal (default 1000). | |
| payment_fee_percent | No | Override payment fees %. | |
| platform_fee_percent | No | Override the platform fee %. | |
| affiliate_commission_percent | No | Affiliate creator commission % (TikTok Shop default 15). | |
| social_contributions_percent | No | Social contributions and taxes as % of revenue (France micro-entreprise default 12.3). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, and the description is consistent with a pure, read-only computation. It adds useful output context: the GO/RISKY/NO-GO verdict, the post-VAT/post-fee payout, and the levers (minimum price, max cost, break-even ROAS, max ad cost). It says nothing about how fee/VAT defaults are resolved or how confident the verdict is, which matters because the result depends heavily on those defaults.
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 purpose comes first, then the outputs, then the triggers. The three-sentence structure fits the tool's large input surface. A little redundancy from fixing the brand name and repeating 'margin', but it is still efficient.
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, yet the description spells out the return value well: a verdict tier, the per-sale take-home after VAT, fees, affiliate, payment, returns and social contributions, plus the specific levers and break-even ROAS. For a 21-parameter tool, that level of detail about what comes back is what an agent needs to choose it.
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 every parameter — channel, country, ships_from, returns, ad cost — is already documented. The description only echoes the two required inputs ('a selling price and a delivered cost') and does not explain how the 19 optional overrides interact with the country/channel defaults. Baseline 3 is the right call.
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?
Specific verb and resource: takes a price and delivered cost and returns a margin verdict plus breakdown. The stated scope is unmistakable. It never names the compare_channels sibling, so an agent must infer on its own that this tool evaluates one product while the sibling compares several — the only thing keeping it off 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 final sentence gives concrete triggers: 'if a product is profitable', 'what margin or fees they will have', or 'how to price it'. That covers most realistic intents. It gives no when-not-to-use rule and never points at compare_channels for multi-channel comparisons, so usage is clear but not fully routed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compares the same product (price, delivered cost) across TikTok Shop, Amazon, Etsy, eBay and an own online store in one country, with the verdict and net kept per sale on each channel.
| Name | Required | Description | Default |
|---|---|---|---|
| cost | Yes | Delivered cost per unit: product + packaging + shipping to the customer. | |
| price | Yes | Selling price paid by the customer, tax included (e.g. 24.90). | |
| channel | No | Where it is sold: tiktok (TikTok Shop), amazon, etsy, ebay, boutique (own store, e.g. Shopify), physique (in person), autre (other). | |
| country | No | Store country: FR, BE, DE, ES, IT, IE, UE (other EU), UK, US, XX (other). Sets currency, VAT and default fees. | |
| language | No | Language of the answer (default en). | |
| ships_from | No | Where parcels ship from (matters for TikTok Shop in the EU). | |
| vat_percent | No | VAT rate % (default: standard rate of the country; 0 for VAT exemption). | |
| delivery_days | No | Business days from order to delivery (optional, used for the verdict). | |
| stock_quantity | No | Units in the first stock order (default 50). | |
| returns_percent | No | Returns provision % (default 5). | |
| samples_percent | No | Free samples as % of units sold. | |
| ad_cost_per_sale | No | Average ad spend per sale. | |
| discount_percent | No | Promotion % off the price. | |
| shipping_charged | No | Shipping paid by the customer, if any. | |
| fixed_fee_per_order | No | Override the fixed fee per order. | |
| monthly_fixed_costs | No | Monthly fixed costs (tools, subscriptions). | |
| monthly_profit_goal | No | Monthly net profit goal (default 1000). | |
| payment_fee_percent | No | Override payment fees %. | |
| platform_fee_percent | No | Override the platform fee %. | |
| affiliate_commission_percent | No | Affiliate creator commission % (TikTok Shop default 15). | |
| social_contributions_percent | No | Social contributions and taxes as % of revenue (France micro-entreprise default 12.3). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish that this is a read-only, non-open-world operation. The description adds useful behavioral context by saying the tool produces a verdict and net kept per sale on each channel, though it omits limitations and assumption details that might affect results.
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 front-loaded sentence with no wasted wording. It efficiently names the comparison scope, channels, country constraint, and result shape.
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 rich 100% schema coverage and read-only annotations, the description provides enough high-level context to understand the tool's purpose and output shape. It is slightly thin for a 21-parameter tool and does not explain how optional assumptions affect the comparison, but the schema fills those 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?
Schema description coverage is 100%, so all 21 parameters are already documented in the schema. The description mentions key inputs like price, delivered cost, channels, and country, but it does not add meaning beyond what the 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 states a specific verb and resource: comparing the same product's price and delivered cost across named sales channels in one country. It is clear what the tool does, but it does not explicitly differentiate itself from the sibling tool calculate_margin.
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 multi-channel comparison within one country, but it does not state when to use it versus calculate_margin or when it should not be used. Usage is inferable but not explicitly guided.
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.
calculate_margincompare_channelsTrue net profit and breakeven price for eBay, Etsy, Poshmark, Mercari, Depop, Whatnot, TikTok Shop.
Landed cost, fees & profit calculators for cross-border Amazon, TikTok Shop and Shopify sellers.
Margin, lead time, SKU mapping and price-ladder maths for dropshipping. 4 of 6 free.
Hosted Etsy, eBay and Amazon FBA/FBM fee, profit, margin and target-price tools. Pay per result.
Add one secure layer between your agents and this server.