Luxor Plastic Cards

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

Adds real context beyond the annotations: a human designer emails a proof and nothing is printed until the user approves it, and the checkout_url only appears when online payment is enabled. It does not warn that a second call creates a second real order (annotations only say idempotentHint=false) or how to cancel one, which is the main behavioral gap for a live-money mutation.

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?

Three sentences, front-loaded with what the tool does and returns, then the production/proof caveat, then the confirmation precondition. Every sentence carries information the schema and annotations do not.

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?

Compensates for the absent output schema by naming the return values, and explains the fulfillment workflow an agent needs to set user expectations. It is not fully complete for an 11-parameter open-world mutation: pricing modifiers (sets, rush, next_day_air, promo_code) and duplicate-order risk go undocumented.

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 45% schema coverage the description must compensate, and it does for design_notes (enumerates the card text fields and style/logo instructions). It says nothing about the other 45% — sets vs quantity multiplication, rush, next_day_air, blind_dropship, promo_code, artwork_urls — and the schema's per-parameter descriptions for those are sparse or absent.

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 and resource ('Creates a real Luxor plastic business card order') and names what comes back (order reference, quote, Stripe checkout_url). The word 'real' plus the checkout link sharply separates it from get_quote, which only prices an order.

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?

Gives a concrete precondition: confirm material, quantity, total price and shipping address with the user before calling. That implies a quote step precedes it, but it never names get_quote or says to use search_designs to obtain template_url, so the routing to siblings is only inferable.

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 critical business logic not found in annotations, specifically the discount rule: 'they do not stack; the larger discount wins.' This is vital information for the AI to predict output or handle user expectations accurately.

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, dense sentence that front-loads the core purpose. Every word contributes to defining the tool's function and scope without unnecessary fluff.

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 complexity of an order (7 parameters, multiple delivery options, and discount logic) and the absence of an output schema, the description is exceptionally complete in outlining the calculation parameters and inherent rules.

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 71% schema coverage, the description adds significant value by elaborating on critical enum values (e.g., defining the differences between 'clear', 'frosted', and 'solid' materials). This helps the agent select the correct parameter even when given high-level user requirements.

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 defines the action (Calculates the exact total) and the resource (an order). It immediately positions the tool as the price determination method, differentiating it from order fulfillment or catalog listing siblings.

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?

While it doesn't explicitly say 'Use this before create_order', it lists the full scope of factors it calculates (material, rush, air, etc.). This comprehensive list provides clear usage boundaries and contexts for gathering user requirements before using the tool.

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 establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: prices include shipping, every quantity tier is returned, and optional fees and turnaround times are included, which tells the agent what to expect in the payload.

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 tightly packed sentences, no filler. The content inventory comes first, followed by the routing directive, so the most actionable instruction is easy to find.

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 fully enumerates the return payload: materials, specs, all quantity tiers, prices with shipping included, turnaround times and optional fees. For a zero-argument listing tool that is everything an agent needs to call it and interpret the result.

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 takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly focuses on output content rather than inventing parameter guidance.

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: returns Luxor's 30mil plastic business card materials, specs, quantity tiers with prices, turnaround and fees. It enumerates the exact content, which distinguishes it from get_quote and search_designs without the agent opening any 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?

"Call this first when a user asks about plastic business cards, prices or options" gives an explicit trigger and even orders it ahead of downstream tools. It stops short of naming get_quote or stating when not to use this (e.g., custom or non-plastic quotes), so it is clear but not fully exclusionary.

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 openWorldHint=false, so the safety profile is covered. The description adds that a customer email is needed alongside the reference, hinting at an identity-scoped lookup, but it does not say whether the email must match the order's own email or what happens on mismatch.

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?

A single sentence that front-loads the action and names both required inputs with an inline format example. No filler.

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 simple two-parameter read tool this covers invocation adequately, but there is no output schema and no description of what a status lookup returns (status values, order details, error shape), which is the main thing an agent needs to interpret the result.

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 0%, so the description carries the burden, and it does add value: an example reference format ('C-AB-12345') and the clarification that the email is the customer's. It still omits case sensitivity, whitespace handling, and what a mismatched email does, but it compensates meaningfully for the empty 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?

States a specific verb and resource ('looks up an existing order') and names both lookup keys, which is enough to distinguish it from create_order and the other siblings. It does not explicitly contrast itself with alternatives, so it falls short of 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?

'Existing order' implies the precondition that the order must already exist, but there is no explicit when-to-use / when-not-to-use guidance and no mention of what to do when the reference or email doesn't match. Usage is inferable rather than stated.

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 mutation, open-world, and non-idempotency. The description adds genuinely new context: this ships a physical kit to a US address and describes exactly what is in it. It omits duplicate-request or rate-limit behavior, which is minor here.

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 short sentences, front-loaded with what the tool does, followed by the call condition. Nothing is padded or repeated from 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?

The tool's purpose and the US-only constraint are covered, and annotations carry the safety profile. However, for an 11-parameter request with no output schema, the description says nothing about the optional fields or what a successful submission yields, leaving real 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 coverage is only 27% across 11 parameters, and the description names no parameters at all. Optional fields like notes, industry, company and phone are left unexplained, so the description does not compensate for the coverage gap where it is expected to.

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 (mails) and resource (free Luxor sample kit) with contents spelled out (clear, frosted, solid white 30mil cards). It is immediately distinguishable from create_order and list_products, the nearest siblings.

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?

"Only call this when the user has asked for samples and provided their details" gives an explicit precondition gate. It does not name an alternative for users who want to buy, but the when-to-use condition is 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?

Annotations already declare readOnlyHint=true and openWorldHint=false; the description corroborates the closed-catalog nature ('Luxor design template pages') and adds genuinely useful context about what is returned (names, page URLs, preview images the user can open). It stops short of describing result count, default result size, or the 25-item cap implied by the limit parameter.

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 tight sentences, zero filler, with the core purpose front-loaded and the return summary following. Every clause carries information the agent needs.

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 simple two-parameter read tool with annotations and no output schema, the description covers purpose, input style, and return contents adequately. The only meaningful gap is result-size/pagination behavior via the undocumented limit parameter.

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 only 50%: 'query' is documented in the schema and the description enriches it meaningfully with example industry phrases, which is real added value. However, the 'limit' parameter (default 8, max 25) is never mentioned in the description and is undocumented in the schema, so half the parameter surface remains unexplained.

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 ('Finds') plus a well-defined resource ('Luxor design template pages') scoped to a profession or industry, with concrete example queries ('roofing', 'med spa'). An agent can immediately tell this apart from the order/product siblings. The second sentence even names what comes back, removing ambiguity about output shape.

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?

Usage is implied rather than stated: the examples signal that queries should be profession/industry phrases, but there is no explicit 'use this when…' framing and no mention of alternatives or when not to call it. An agent can infer the context, but nothing routes it explicitly against other options.

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