Moltline Dropship Economics

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

Beyond the annotations (readOnly, idempotent), the description adds concrete behavioral context: never raises a protocol error, returns an error object with corrective guidance, and explicitly confirms that retrying is safe. This significantly exceeds what annotations already 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 longer than average but every sentence adds value (purpose, usage, example, error handling, safety). The 'FREE' note is unnecessary noise but doesn't obscure the core content. Format is front-loaded with purpose and example.

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 (5 params, output schema), the description covers all key aspects: calculation logic, example output, error behavior, idempotency, and usage context. No significant gaps remain.

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 a concrete example with typical inputs and outputs, clarifying the buffer concept and error format, which helps agents understand parameter relationships 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 function: turning supplier and transit times into a promise date, with a specific example. It distinguishes itself from siblings by explicitly saying it is not for shipping costs and pointing to a separate shipping server.

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 guidance ('when writing a shipping policy or answering when will it arrive') and an explicit exclusion ('Not for what the shipping costs'), which clearly differentiates it from related tools.

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 read-only and idempotent behavior, but the description adds valuable context beyond annotations: it details error handling ('never raises a protocol error — it returns {"error": ...}'), retry safety, and a caveat about ad_cost_per_order defaulting to 0 being misleading. This goes above and 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-structured and front-loaded with the core purpose, followed by an example, usage guidance, and error behavior. Every sentence earns its place; the 'FREE.' is slightly extraneous marketing but not distracting. The length is justified given the tool's complexity.

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 is complete for a calculator-style tool: it explains the math, shows a full input/output example, covers error handling, and gives usage context. Combined with the rich annotations and output schema, no critical information is missing for an agent to invoke this 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?

With 100% schema description coverage, the schema already documents each parameter's meaning. The description adds a concrete typical input example and highlights a common pitfall (ad_cost_per_order default), which enhances understanding beyond the schema alone. It stops short of being exhaustive but is clearly helpful.

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 what the tool does: 'Show what one sale actually leaves after every cost' and details the calculations (subtracting costs, break-even price). It explicitly distinguishes itself from siblings: 'Not for a whole tiered price list — that is price_ladder — and not for the effect of returns, which is returns_impact.'

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 when-to-use guidance is given: 'Use before listing a product.' It also names specific alternatives for scenarios the tool does not handle (price_ladder for tiered pricing, returns_impact for returns), making the decision boundary clear.

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 annotations already declare readOnlyHint and idempotentHint, but the description adds critical behavioral detail: 'Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.' This goes beyond the annotations by detailing error handling and retry safety, which is valuable context for an agent.

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: a clear opening purpose, a practical example, usage guidance, error handling, and retry advice. Each sentence adds value—no verbosity or repetition. It is front-loaded with the most critical information (purpose) and then progressively adds detail, making it easy to scan.

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 6 parameters (including optional ones), an output schema (not shown but indicated), and annotations covering safety, the description is remarkably complete. It covers the decision context, an example output, error behavior, and where it fits relative to siblings. There are no significant gaps; even the premium licensing note is a minor extra. This is comprehensive for a tool of this complexity.

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 baseline is 3. The description adds a concrete example (typical input and output) that clarifies how the parameters interact (e.g., unit_cost, moq, cash_available, lead_time_days produce moq_cost, months_of_cover, etc.). This example enriches parameter understanding beyond the schema's individual descriptions, making the tool's usage more intuitive. However, it does not detail individual parameter nuances, so a 4 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?

The description opens with a clear statement of purpose: 'Decide how much to order against demand, lead time and the cash you have.' It specifies the resource (how much to order) and the criteria. It also distinguishes itself from a sibling tool explicitly: 'Not for the margin each unit earns — that is margin_check.' This is specific and 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 usage context: 'Use before committing to a supplier's minimum.' It also states an alternative tool for a different purpose ('margin_check'). This directly addresses when to use this tool and when not to, with a named alternative, exceeding the minimum requirement.

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 adds context beyond annotations: it notes the fee inclusion nuance, error-handling behavior ('never raises a protocol error — returns {error}'), and idempotent/read-only guarantee (though idempotent/readOnly are already in annotations). The error behavior and fee subtlety are extra value. 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 a single well-structured paragraph that front-loads the primary purpose as an imperative, then gives usage guidance, an example, and error behavior. No fluff—every sentence adds information. Slightly long but justified by complexity.

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 complexity (6 params, some interdependent fee logic), the description covers the core formula, provides a concrete input/output example, explains the error behavior, and explicitly states the read-only/idempotent nature (authoritative even if annotations also mention it). With an output schema presentished, the example covers return structure. This is fully sufficient for an agent to invoke 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 coverage is 100% with detailed descriptions, so baseline is 3. The description adds value by explaining the fee calculation nuance (not simply cost/(1-margin)) and providing a concrete example input that clarifies how parameters combine. This pushes it above baseline.

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 an explicit purpose: 'Work backwards from the margin you want to the price you must charge. FREE.' It clearly names the tool's function and distinguishes it from sibling margin_check by saying 'Not for checking one price you already have — that is margin_check.' The verb-resource pairing is specific.

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?

Directly states when to use: 'setting a price list' and explicitly excludes when not to use: 'Not for checking one price you already have — that is margin_check.' This is the clearest form of usage 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?

The description discloses error handling ('never raises a protocol error — it returns an error object') and idempotency/read-only nature ('Every call is read-only and idempotent'), which align with the annotations. This adds useful behavioral context beyond the annotations themselves.

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 somewhat verbose and includes extraneous content like 'PREMIUM (license)' and repetitive phrasing. While it is structured (purpose, example, usage, errors), it could be more concise and 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 complexity (7 parameters, output schema present), the description provides a typical input/output example, usage guidance, and error behavior. The schema covers parameter details, so the description sufficiently rounds out the context without being exhaustive.

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 parameter descriptions (100% coverage), so the baseline is 3. The description adds a concrete example with values and output, illustrating how parameters interact, which enhances understanding beyond the schema alone.

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 calculates the impact of return rates on profit margins, with an example input/output. It also distinguishes itself from the sibling tool 'margin_check' by indicating it is not for pre-returns margin. However, the phrasing is somewhat poetic and includes irrelevant 'PREMIUM (license)' text.

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 explicitly gives when to use: 'Use when a category's returns are high enough to argue about' and when not to use: 'Not for the pre-returns margin itself — that is margin_check.' This provides clear decision guidance relative to sibling tools.

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, so the description rightly doesn't relitigate those. It adds genuine value with the error contract (never raises a protocol error, returns a structured error object) and the retry-safety framing. Minor point: the 'read-only and idempotent' sentence mostly restates annotations, but the error-behavior detail justifies a 4.

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?

Efficiently front-loaded with a value-proposition hook, then organized into clean paragraphs: rule explanation, worked example, usage timing, and error contract. Every sentence adds information; nothing is redundant, and the only blemish is the cryptic standalone 'FREE.' that appears to be a leftover artifact.

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 validation tool with an output schema and comprehensive annotations, the description leaves nothing unresolved: it explains the core rule, shows a realistic request/response interaction, gives the trigger conditions, the exclusion, the error shape, and safety guarantees. No meaningful gap for the agent's decision-making.

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 described input/output example earns the extra point by showing what counts as a violation (empty string, duplicate supplier SKUs), which enriches the otherwise minimal 'mapping' parameter definition and sets correct expectations for the response shape.

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 opening sentence uses a specific verb+resource ('Find the breaks in a supplier-to-store SKU map'), and the one-to-many vs many-to-one rule clarifies exact semantics. The purpose is completely distinct from all sibling tools (lead_time, margin_check, moq_planner, price_ladder, returns_impact), leaving no room for confusion.

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 guidance ('Use before importing a mapping or handing one to a fulfilment app') and an explicit when-not-to statement with a named alternative ('Not for validating Shopify's CSV columns — that is the shopify server'). This is a textbook example of exclusion-based differentiation.

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