agentee

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

Annotations are minimal (no readOnly, destructive, etc.). The description adds behavioral context: the tool requires a finished print and integrates with the checkout flow. It does not discuss side effects, error states (e.g., if print_id is not done), or idempotency. While helpful, it lacks depth for full transparency.

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 short and front-loaded with the main action. The use of abbreviations and parentheses ('print_id (must be done)') is efficient but slightly cryptic. Every sentence adds value, but it could be slightly more readable.

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 relative simplicity (4 params, output schema present), the description covers the essential workflow: precondition on print_id, parameter hints, and follow-up steps. It lacks error handling or validation details, but for a cart addition tool, it is reasonably complete.

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 baseline is 3. The description adds value by clarifying preconditions (print_id must be done) and specifying the valid set for product ('same set as studio_generate'). This goes beyond the schema's descriptions.

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 action: putting a finished custom print into the cart. It distinguishes from sibling 'add_to_cart' by specifying 'custom print' and requiring a finished print_id. The verb 'Put...into the cart' 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?

The description provides usage context by listing arguments and their constraints (e.g., print_id must be done, product set same as studio_generate). It also mentions the subsequent checkout flow (get_order_preview -> prepare_order), guiding the agent on typical usage. However, it does not explicitly state when to avoid this tool or provide alternatives.

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 indicate a write operation (readOnlyHint=false) and non-destructive nature. The description adds useful context by stating it returns the updated cart and specifying where args come from, improving transparency.

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?

Extremely concise: two sentences. The first states the purpose, the second lists arguments with brief semantics. No wasted words; every sentence earns its place.

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?

Covers inputs and output (returns updated cart). Given the tool's moderate complexity and full schema descriptions, it provides sufficient context for an agent. Missing edge cases like stock checks are acceptable for a cart add tool.

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 descriptions for each parameter. The description adds value by clarifying sources (good_id from search/get_product) and defaults (qty default 1), and by noting fabric is optional. This goes beyond repeating schema info.

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?

Clearly states verb and resource: 'Add a product to the user's cart.' The description is specific about what it adds, but does not explicitly differentiate from sibling tools like add_custom_to_cart or cart_update.

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?

Implies usage by specifying that good_id comes from search/get_product and size must match product sizes, but does not provide explicit when-to-use or when-not-to-use guidance compared to alternatives.

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 indicate idempotent (idempotentHint=true) and non-destructive (destructiveHint=false). Description adds 'server-checked' and clarifies return behavior, but does not elaborate on side effects or authentication needs beyond what annotations convey.

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?

Extremely concise: two sentences that cover purpose, behavior, and return format with no wasted words. Information density is high.

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?

Covers the essential behavior and return values. Given that an output schema exists (indicated by context), the description complements it well. Could mention idempotency or the cart scope, but sufficient for a simple tool.

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 a clear parameter description. The description repeats 'Args: code' without adding additional details beyond the schema. Baseline 3 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?

Clearly states the tool validates and applies a promo code to the cart, specifying the server-side check. Distinguishes itself from siblings like remove_promo by focusing on application.

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?

Describes the return format (new discount/shipping/total or applied=false with reason), guiding the agent on what to expect. Does not explicitly mention when to use versus other cart tools, but the purpose is strongly implied.

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 destructiveHint=true, so the description's 'Remove' is consistent. No additional behavioral details are provided (e.g., irreversibility, error handling). The description adds minimal value beyond 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 extremely concise with only two short sentences, no unnecessary words, and front-loads the key 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?

For a simple single-parameter tool with a clear purpose and good annotations, the description is sufficient. It could mention that the index must be valid, but the schema covers that. The existence of an output schema reduces need for return value explanation.

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 description repeats the schema's parameter description (index from view_cart). With 100% schema coverage, the description adds no new semantic meaning. Baseline score of 3 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 clearly states the action (remove), the resource (cart line), and the method (by index from view_cart). It effectively distinguishes this tool from siblings like add_to_cart and cart_update.

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 implicitly guides usage by indicating the index should come from view_cart, suggesting a prerequisite. However, it does not explicitly list when not to use or compare with alternatives like set_cart_quantity.

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 states 'qty (0 removes)', indicating a destructive action, but annotations set destructiveHint=false. This is a direct contradiction, undermining the agent's ability to gauge side effects. No additional behavioral context (e.g., permissions, irreversibility) is provided.

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 sentence, concise and front-loaded. It covers essential usage in a compact format. Minor improvement could separate removal guidance from general changes, but overall 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?

Given an output schema exists, return values need not be described. However, the tool interacts with a cart context; the description should mention that view_cart must be called first to obtain the index. It mostly suffices but lacks a brief note on error conditions (e.g., invalid index, unavailable size/fabric).

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 all parameters have descriptions. The description echoes 'qty (0 removes)', but this adds no new meaning beyond the schema. Baseline score of 3 is appropriate; it does not degrade or enhance.

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 verb 'change', the resource 'a cart line', and the specific indexing method 'by its index (from view_cart)'. It enumerates modifiable fields (qty, size, fabric), distinguishing it from sibling tools like set_cart_quantity and cart_remove by accommodating multiple modification types.

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 prerequisite (call view_cart to get index) and explains parameter usage (qty=0 removes). However, it does not explicitly compare to alternatives like cart_remove for removal or set_cart_quantity for quantity-only updates, leaving some ambiguity about when each sibling is preferred.

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, non-destructive; description adds the critical distinction that the agent never pays, enhancing transparency beyond 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?

Two concise sentences with no wasted words, front-loading the core purpose and key constraint.

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?

With no parameters and an output schema, the description fully explains the tool's function and behavior for accurate selection and invocation.

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?

No parameters exist, so the description correctly focuses on purpose and output; schema coverage is complete.

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 gets a URL for the human to review and pay, distinguishing it from siblings by emphasizing the agent's non-involvement in payment.

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 clarifies that checkout is human-only, implying the agent should not attempt payment, but does not explicitly list when not to use or suggest alternatives among many siblings.

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, destructiveHint. Description adds behavioral context by specifying the filter on live status and default limit, aligning perfectly with annotations without contradictions.

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 sentences, highly concise with front-loaded purpose. No unnecessary words; every piece of information earns its place.

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 list tool with one optional parameter and an output schema (beyond scope to describe), the description fully covers what the tool does and the key parameter. No gaps given the tool's simplicity.

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% and schema already documents the limit parameter with description. Description adds the default value (50) and indicates optionality, which adds minimal extra value 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?

Description clearly states the tool lists the user's own published designs filtered by live status (on sale/hidden/pending). This specific verb+resource scope distinguishes it from sibling tools like designer_stats or studio_generate.

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 states 'user's own published designs', indicating the tool is intended for the authenticated user. No explicit when-not or comparison to alternatives, but context from sibling tools makes the use case 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 idempotentHint=true. The description adds the conditional 'if they are a designer-partner', which is useful behavioral context. It does not discuss authentication or rate limits.

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?

Single sentence that efficiently lists the returned fields. Could be slightly more structured but is reasonably concise.

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 no parameters, rich annotations, and an output schema, the description covers the tool's purpose and output. The conditional access note adds necessary completeness.

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?

No parameters exist, so baseline 4 applies. The description does not need to add parameter meaning.

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 it retrieves designer-program stats and lists specific fields. However, it does not explicitly differentiate from sibling tools like designer_designs or designer_submissions, so it loses a point for sibling distinction.

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?

No guidance on when to use this tool versus alternatives. The description does not mention contexts where other tools would be more appropriate.

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 destructiveHint as false, so the safety profile is clear. The description adds context about the specific moderation states returned, which is useful. No additional behavioral details (e.g., pagination, authentication) are provided, but for a read-only list tool this is acceptable.

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 extremely concise at one sentence plus a parameter reference. It is front-loaded with the key purpose. However, the structure is fragmented (two short phrases rather than a complete sentence), which slightly reduces readability.

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 has one optional parameter and an output schema (not shown). The description addresses the scope (user's own submissions), the set of statuses, and the limit parameter. No major gaps; for a simple listing tool, it is mostly complete.

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% for the single parameter 'limit', with documentation of defaults and max. The description merely echoes 'Args: limit?' without adding new meaning. Baseline score of 3 is appropriate when schema already covers parameter semantics.

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 identifies the resource as 'the user's Studio publications in moderation' and lists the statuses (in review, in catalog, needs changes), which clearly distinguishes it from sibling tools like 'designer_designs' or 'studio_status'. However, it lacks an explicit verb like 'Lists' and is phrased as a noun phrase, slightly reducing clarity.

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 no guidance on when to use this tool versus alternatives. Given 27 sibling tools including 'designer_designs' and 'studio_status', explicit context about moderation state filtering would help the agent decide when to invoke this 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds that prices are server-computed, which is relevant context. No contradictions.

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, front-loaded sentence that efficiently communicates the tool's purpose and key benefit. No extraneous text.

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 no parameters, excellent annotations, and the presence of an output schema (not shown but indicated as true), the description is fully sufficient for an agent to use 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?

There are no parameters, so the schema coverage is 100%. The description adds no parameter info, but none is needed. The tool is well-defined with zero ambiguity.

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 provides a full order summary including line items, promo/discount, shipping, address, and grand total. It distinguishes from siblings like prepare_order and other cart tools by focusing on preview.

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 explicitly says 'to show the human before ordering', which implies a confirmation step. No explicit when-not or alternatives, but the purpose is clear enough for correct usage.

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, destructiveHint=false, idempotentHint=true. The description adds a list of returned fields but no new behavioral traits (e.g., error handling or missing product). Consistent, but adds minimal value beyond 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?

One sentence plus a clear arg note. Front-loaded with purpose, no unnecessary words.

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?

Simple tool with one parameter; description lists key return fields. Output schema exists, so return format is covered. Complete for the tool's 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 has 100% coverage with description 'Product code from search_products results.' The description reinforces this source. Adds value by identifying where the code comes from.

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 'Full details of one product by its code' and lists what is included (sizes, fabrics, per-variant price, design about text). This distinguishes it from sibling tools like search_products or add_to_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?

Explicitly says 'code (from search_products)', guiding the agent to use search_products first. No explicit when-not or alternatives, but sufficient for a simple retrieval 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 declare readOnlyHint and idempotentHint, describing the tool's safety. The description adds that it returns past-order addresses, providing behavioral context without contradicting 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 a single sentence with front-loaded purpose and a practical suggestion, containing no unnecessary words or structure.

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 zero parameters, comprehensive annotations, and an existing output schema, the description provides complete context for a simple retrieval tool, covering purpose and use case.

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?

There are zero parameters, so the baseline is 4. The description does not need to add parameter meaning, and it focuses on the tool's purpose instead.

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 returns shipping addresses from past orders, distinguishing it from sibling tools like set_shipping_address or get_shipping_options by specifying the use case for returning buyers.

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 implicitly guides use by suggesting to offer these addresses to returning buyers, but lacks explicit when-not or alternative tool references. However, the context is clear enough for an agent to infer appropriate usage.

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 indicate readOnly, idempotent, non-destructive. Description adds that it returns price, ETA, and free threshold context, which is useful beyond 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?

Single sentence, no wasted words, front-loaded with key 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?

For a tool with no parameters and an output schema, the description is sufficient to explain what it returns and the context.

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?

No parameters exist (schema coverage 100%), so description is not required to add parameter details. It correctly implies state dependence on current cart/address.

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 retrieves available shipping methods for the current cart/address, including price and ETA, with a note about free shipping. This distinguishes it from sibling tools like set_shipping_method.

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 purpose implies usage when needing to view shipping options before selecting one, but no explicit guidance on when to use vs alternatives (e.g., get_order_preview) or when not to use.

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 indicate readOnlyHint=true and idempotentHint=true, so the description adds value by detailing automatic application and fit preference behavior. No contradictions.

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 sentences, no wasted words, front-loaded with purpose and immediate usage guidance.

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 zero parameters and presence of output schema, the description covers all needed context: what it does, when to call it, how to use result, and integration with add_to_cart.

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?

No parameters exist, and schema coverage is 100%. The description effectively explains what the tool returns and how to use it, adding full meaning beyond 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?

The description clearly states it returns the shopper's saved default size and fit, with specific verb 'Return' and resource 'default size and fit'. It distinguishes from siblings like set_user_prefs by focusing on retrieval and automatic application.

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 instructs to call this BEFORE asking for a size, and describes how to apply the result automatically and prefer matching fit. No ambiguity about when to use it.

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?

Description adds minimal behavioral context beyond annotations: it specifies that collections are 'active' and 'curated', and returns slugs and urls. Annotations already declare readOnly, idempotent, non-destructive. No contradictions.

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?

Description is two sentences and to the point. The second sentence 'Args: limit?' is slightly awkward but not verbose. Overall concise and front-loaded with purpose.

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 list tool with an output schema, the description covers the key points: what is listed and what fields are returned. Omission of pagination or filtering details is acceptable given optional parameters and output schema.

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% and describes the 'limit' parameter with default and max. The description only repeats 'Args: limit?' without adding new information, so baseline of 3 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?

Description clearly states the verb (List), resource (active curated collections), and what is returned (slugs and urls). The phrase 'themed landing pages' adds context that distinguishes it from sibling tools related to products, cart, and orders.

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?

No guidance on when to use this tool versus alternatives. The description does not mention when not to use it or provide context for selection among 25 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, destructiveHint=false. The description adds that it returns 'fulfilment status' but does not disclose additional behavioral traits (e.g., auth, rate limits) beyond what annotations 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?

Single sentence with inline parameter explanations. No wasted words, purpose is front-loaded. Highly 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?

With output schema present and full annotation coverage, the description adequately covers the look-up functionality. It mentions result type (fulfillment status), which is sufficient. Slightly lacks edge case details, but overall complete.

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 good parameter descriptions. The description adds extra context: default limit of 5 and the meaning of omitting number (returns most recent). This enhances understanding beyond 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 looks up user's recent orders or a specific order by number, and returns fulfillment status. The verb 'look up' and resource 'orders' are specific, and it distinguishes from sibling tools like 'prepare_order' or 'get_order_preview'.

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: use to check order status. No explicit guidelines for when to use vs alternatives, nor when not to use. The description provides parameter-level guidance but not tool-level usage context.

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 indicate readOnlyHint=false and destructiveHint=false. The description adds that the tool creates a draft order (non-read) and the human pays later, but does not disclose other behaviors like authorization needs or side effects on the cart. Adds marginal value beyond 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?

Two sentences: first states purpose and output, second gives usage guidance. Extremely concise with no wasted words, and front-loaded with critical 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?

Given no parameters and an output schema (return fields listed), the description covers the essential information. However, it does not address edge cases like missing cart or address. For a simple tool, it is fairly complete.

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?

Input schema has zero parameters, so schema coverage is 100%. The description implicitly defines the inputs as 'cart + address + promo' (presumably from state), adding meaning beyond the empty schema. With no parameters, this is sufficient.

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 creates a draft order from the cart, address, and promo, and lists the specific return fields (checkout_url, draft_id, expires_at). This provides a specific verb and resource, and distinguishes it from siblings like get_order_preview.

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 instructs to call get_order_preview and confirm with the human first, and states that the agent never pays. This provides clear when-to-use and when-not-to-use guidance, effectively differentiating from 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?

The description does not contradict annotations (idempotentHint=true, destructiveHint=false) but adds no additional behavioral context beyond what annotations already provide. No mention of side effects, errors, or edge cases.

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 clear sentence with no unnecessary words. It is front-loaded and 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?

Given the tool's simplicity (no parameters, output schema present), the description is adequate. It could mention that the promo must be applied for the action to have effect, but the current description is sufficient.

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 has no parameters (0 params), and schema coverage is 100%. The description adds no parameter details, but none are needed. Baseline score of 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 clearly states the verb 'remove', the resource 'promo code', and the context 'from the cart'. It directly distinguishes this tool from its sibling 'apply_promo' which adds a promo code.

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 usage when a promo code is applied and needs removal, but it does not explicitly state when to use this tool versus alternatives like 'cart_remove' (which removes cart items) or provide any context about prerequisites.

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 mark it as readOnly and idempotent. The description adds that it returns product cards with specific fields and notes the max limit. It does not disclose additional behavioral traits like authentication needs or result ordering.

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 concise (two sentences) and front-loaded with the tool's purpose. It efficiently lists parameters with examples, though the use of abbreviations and parentheses slightly reduces readability.

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 that an output schema exists, the description adequately covers return value shape (good_id, price, url). It also explains all 5 parameters and constraints like limit<=48. Missing details like ordering or pagination are minor.

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 baseline is 3. The description provides examples (e.g., 'cat', 'neon koi') and notes comma-separated themes, adding some value over schema but not substantially more.

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 it searches the allover.art catalog and lists the parameters. It does not explicitly differentiate from siblings like get_product or list_collections, but the verb 'search' and the catalog scope make its purpose distinct.

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?

No explicit 'when to use' or 'when not to use' guidance is given. The description implies it is the primary search tool, but does not mention alternatives or situations where another tool should be preferred.

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 indicate idempotentHint=true and readOnlyHint=false. Description adds the key behavioral detail that qty=0 removes the line, which is beyond annotations. 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?

Two sentences, efficient wording, front-loaded with core action. Every word adds value, no redundancy.

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 tool with an output schema, the description covers essential usage including index source and removal behavior. No gaps given the tool's 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 coverage is 100% with detailed descriptions for both parameters. The description repeats the same info from the schema without adding new meaning, thus baseline 3 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 clearly states the verb 'change' and resource 'cart line quantity', and distinguishes from siblings like cart_remove and add_to_cart by specifying index-based modification and qty=0 removal behavior.

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 clear context by linking index to view_cart and noting qty=0 removes the line. It lacks explicit when-not-to-use or alternative tools, but the context is sufficient for the simple cart operation.

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 the word '(validated)', indicating input validation. Annotations already provide idempotentHint=true and destructiveHint=false. No contradiction. The validation context is useful beyond annotations but minimal.

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 short, front-loaded with the action, and includes a compact args list. No wasted words, though the args list is somewhat redundant with 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 description covers the basic action but lacks context about what happens on validation failure, order state prerequisites, or relationship to sibling tools like 'get_saved_addresses'. With an output schema present, return values are not needed.

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% already describing all parameters. The description lists args with optionality marker for zip, but this adds minimal value since schema already marks zip as not required.

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 purpose: 'Set the shipping address for this order (validated).' The verb 'set' with resource 'shipping address' is specific. It distinguishes from sibling 'set_shipping_method' which targets a different resource.

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?

No guidance on when to use this tool versus alternatives like 'get_saved_addresses' or 'prepare_order'. No prerequisites or ordering constraints mentioned.

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 indicate idempotentHint=true, destructiveHint=false, and readOnlyHint=false. The description adds no behavioral context beyond what annotations provide, such as side effects or error cases.

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 sentence plus argument list, with no unnecessary words. It delivers essential information efficiently.

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 adequate for a simple tool with one parameter and an output schema, but it lacks context on the tool's effect on the cart or order, and does not explain return values.

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 covers option_id with a description, and the description adds value by specifying it comes from get_shipping_options and providing an example. This exceeds 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 selects a shipping method using an option_id and references the source function (get_shipping_options). This distinguishes it from sibling tools like get_shipping_options and set_shipping_address.

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 usage after get_shipping_options but offers no explicit guidance on when to use versus alternatives like set_shipping_address, nor when not to use this 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?

Description adds context beyond annotations: it explains the benefit and the 'only what user stated' behavior. Annotations already indicate idempotentHint=true and safe, so 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?

Two concise sentences with purpose front-loaded and parameters listed. No extraneous content.

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 simple tool with output schema and full parameter coverage, the description is sufficient for an agent to select and invoke the 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?

Schema coverage is 100%, so baseline is 3. Description provides a compact summary of size range and fit values, adding marginal value over schema descriptions.

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?

Clearly states it saves the shopper's default size/fit to avoid re-entry. Distinguishes from sibling 'get_user_prefs' as the write counterpart.

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 instructs to pass only what the user stated, implying no overwriting of unspecified fields. No explicit when-not to use, but the context 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 indicate readOnlyHint true and destructiveHint false. Description adds context about the credit economy and the tool's role, but does not disclose additional behavioral traits beyond what annotations 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?

Two concise sentences with essential information front-loaded. Every sentence adds value without redundancy.

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 no parameters and presence of output schema, the description fully covers what the tool does and why it should be used. It is complete for a simple read-only balance checker.

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?

No parameters exist, so schema coverage is 100%. Description adds value by explaining the credit system context, which aids in understanding the tool's purpose.

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 checks the user's Studio credit balance using the verb 'Check' and resource 'credit balance'. It differentiates from sibling tools like studio_generate which consumes credits.

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 advises to use this tool before studio_generate, explains the cost (1 credit per generation) and how credits are earned (welcome bonus, buying tee), providing clear when-to-use 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?

Discloses timing (2-10 min), cost (credits, free starter balance), and async behavior (poll studio_status). Adds value beyond annotations (readOnlyHint=false, openWorldHint=true).

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?

Somewhat long but every sentence provides essential info (prerequisite, params, cost). Front-loaded with core action, well-structured for agent parsing.

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?

Comprehensive for a complex tool: covers prereqs, all parameters, cost/time details, async polling, and output schema existence. No gaps given context signals.

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?

Adds meaning beyond 100% schema coverage: clarifies defaults for product, placement; explains preserve=true is free; links background to studio_options; and lists placement options.

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?

Clearly states verb 'Generate' and resource 'custom t-shirt print'. Distinguishes from sibling tools by specifying workflow (call studio_options first) and async nature.

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 instructs to call studio_options first and ask for user input, defining when and how to use. Implicitly differentiates from offspring tools like studio_status.

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 indicate readOnlyHint, idempotentHint, and non-destructive behavior. The description adds workflow context (presenting to human) but does not introduce new behavioral traits beyond what annotations imply.

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 sentences, front-loaded with the key purpose, contains all necessary information without any superfluous text.

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 fully explains the tool's purpose and output (menu of choices) despite having no parameters and an existing output schema. It is complete for a read-only listing tool.

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 zero parameters, baseline is 4. The description adds no parameter info, but schema coverage is 100% (trivially), so no compensation needed.

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 this tool is the starting point for custom-print requests, providing a menu of generation choices (placements, products, backgrounds, engines+costs). It distinguishes itself from siblings like studio_generate by serving as a prerequisite step.

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 explicitly says 'START HERE for any custom-print request' and instructs the agent to present options to the human, asking at minimum for placement and product before calling studio_generate. This provides clear when-to-use and workflow 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?

Annotations already provide readOnlyHint and idempotentHint. The description adds that it returns a preview_url when done, but does not clarify behavior when not done or error states. Given annotations cover safety, the description adds some context but lacks full behavioral disclosure.

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 sentences, front-loaded with purpose, no wasted words. Every sentence adds value.

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 status-checking tool with an output schema, the description explains input, output behavior, and human interaction. Could mention polling or timeout, but adequate for most use cases.

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%, and the description merely repeats that print_id comes from studio_generate. No additional 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?

The description clearly states the tool checks a custom print generation, with a specific verb and resource. It distinguishes from siblings like studio_generate by indicating it's a status check that returns a preview_url.

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 usage after studio_generate by specifying the print_id comes from that tool. It also instructs to show the preview_url to the human. However, no explicit when-not or alternatives are mentioned.

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 destructiveHint. The description adds minimal extra context (browser equivalence), so it meets expectations but does not exceed them.

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, concise sentence with no wasted words. It is front-loaded and 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?

Given no parameters and an existing output schema, the description sufficiently covers the tool's purpose. It lacks mention of potential empty cart states, but the output schema likely handles that.

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?

There are no parameters, so the description is not required to add parameter semantics. Baseline 4 applies.

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 uses the specific verb 'Show' and identifies the resource 'current contents of the user's cart', clearly distinguishing it from sibling tools that modify the cart (e.g., add_to_cart, cart_remove).

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 this is for viewing only ('the same cart they see in the browser'), but does not explicitly state when not to use it or which sibling tools are appropriate for modifications.

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