Standard Blanks

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

Annotations only say it is a non-read-only, non-idempotent, closed-world write; the description adds the substance the agent needs: the cart is not an order, no payment is taken, the returned link expires after 7 days, and there are 40-line / $5,000 caps. That is meaningfully beyond the structured hints.

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?

One core sentence followed by the crucial non-order disclaimer, then the operational limits — all front-loaded, no filler, and every clause (return value, handoff instruction, caps, expiry) carries information an agent acts on.

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 two-parameter tool with no output schema, the description covers what it creates, what it returns (claimUrl), what it deliberately does not do, and the hard limits including expiry, so nothing an agent needs to invoke it correctly is missing.

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 pushes above that by adding a constraint the schema cannot express — a $5,000 merchandise ceiling and the 40-line cap on items, which tells the agent when a request must be split or rejected.

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 ('Create a cart of SKUs and quantities') and names the concrete artifact returned ('claimUrl'), which lets an agent separate it from quote, search_catalog and get_inventory without 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?

Explicitly bounds when-not-to-expect: 'It does not take payment or place an order' and instructs 'Give the shopper the link', making the handoff pattern clear. It stops short of naming the natural alternative (quote) for price-only requests, so routing between the two is left implicit.

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 that this is a safe, idempotent, read-only lookup. The description adds meaningful behavioral detail beyond that: the exact status categories and the 'a dozen or fewer' threshold for 'low', which an agent could not infer from the annotations alone. It does not cover data freshness or why 'unknown' occurs.

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, front-loaded with the outcome categories and followed by the invocation rule. There is no filler and every clause carries information.

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, so the description must explain return semantics, and it does by listing the four possible statuses. The main remaining ambiguity is what happens if both SKU and slug/color/size are supplied, or what 'unknown' signifies operationally.

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 0 required parameters and only 50% schema description coverage, the description supplies the critical dependency rule: use either a SKU alone, or a slug together with color and size. This clarifies how the four optional parameters combine in a way the schema does not enforce.

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 check: whether one variant is available now, and enumerates the possible statuses (in_stock, low, out_of_stock, unknown). This clearly separates it from siblings like build_cart, search_catalog, and quote, though it doesn't explicitly name them.

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 by the availability-checking purpose, and the description tells you how to identify the variant (SKU or slug+color+size). However, it never states when to call this versus get_product or when availability should be re-checked, nor does it exclude any scenarios.

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, idempotentHint, and non-destructive, so the description correctly focuses on behavior beyond that: what data comes back and the conditional expansion triggered by `color`. It doesn't cover failure modes (invalid slug/SKU, neither identifier provided), leaving a small behavioral gap for a zero-required-param lookup.

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?

Front-loaded with the core purpose in the first clause, then the lookup keys, then the returned facets. Dense but every enumeration (decoration methods, size chart) maps to real tool output; only the long decoration-method list is slightly heavy.

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?

No output schema exists, so the description carries the return-value burden and does so thoroughly by enumerating the data fields. The remaining gap is the absence of any statement about precedence or behavior when both/neither of `slug` and `sku` are passed, given that no parameters are required.

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 earns more by explaining provenance (slug from search_catalog, SKU from a variant), the alternate lookup paths, and that `color` must match a name in `colors` and additionally returns that color's sizes with SKUs and availability.

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 ('Details for one product') and immediately distinguishes it from search_catalog by naming it as the source of the slug. It enumerates the returned facets (colors, sizes, size chart, fabric, decoration compatibility), so an agent can tell it apart from get_inventory or search_catalog without opening a 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?

Gives clear entry paths: lookup by slug from search_catalog or by any variant SKU, and explains the conditional use of `color` to expand the response. It doesn't state exclusions (e.g., use get_inventory for stock levels) or what happens when neither identifier is supplied, so guidance is strong but not fully explicit.

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 readOnly, idempotent, and non-destructive behavior; the description adds substantive context: unit price depends on the style's total units, shipping assumptions, estimated-not-guaranteed delivery dates, sales tax calculated at checkout, and 'Creates nothing.' There is no contradiction with 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?

Front-loads the core purpose and output components, then branches on ship_to_zip, then notes tax and the no-write caveat. Dense but every sentence adds decision-relevant information with no repetition.

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?

No output schema exists, but the description enumerates the returned pricing fields and delivery-date behavior; annotations cover safety and the schema covers parameters. This is sufficient for an agent to call the tool and interpret its results 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%, so the baseline is 3; the description adds meaningful semantics for ship_to_zip (ZIP-specific shipping and estimated delivery dates, contiguous-US default when omitted) and the pricing rule for items. It does not restate every schema constraint, such as 1–40 lines or qty maximum, but adds useful meaning 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?

States a specific verb/resource: exact prices for SKUs and quantities, and enumerates the outputs (unit price, merchandise subtotal, shipping, total before tax). The phrases 'as the Standard Blanks cart would charge them' and 'Creates nothing' distinguish it from build_cart.

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 clear context for pricing and explains the ship_to_zip branch, including the contiguous-US fallback and that no delivery dates are given without it. It does not explicitly name build_cart as the alternative for actually creating a cart, so it lacks a full when/when-not routing statement.

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?

Beyond the read-only and idempotent annotations, the description discloses the return shape, the up-to-20 result cap, price units, availability, image and URL fields, color/size matching semantics, and typo/dropped-word signaling. This is substantial behavioral context for a tool with no output schema.

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 front-loaded with purpose and return behavior, then adds only the non-obvious color/size and signal semantics. It is appropriately sized for an eight-parameter search tool with no output 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?

Given the lack of an output schema, the description supplies enough return-value context for an agent to interpret results correctly. It also makes the follow-up workflow clear by naming get_product.

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 already 100%, so the schema carries most parameter meaning. The description adds useful interpretation for query/color/size interactions, especially what matchedColors means and what an empty match implies.

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: searching blank apparel by keywords and filters. It also distinguishes the follow-up path by telling the agent to use the returned slug with get_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?

It gives clear search context and points to get_product for the next step, but it does not explicitly compare against siblings like get_inventory or quote. The implied usage is still strong for a search tool.

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