Server Quality Checklist

Tool Scores

• add_to_cartC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description must carry the burden of behavioral disclosure. It states that the user ID comes from the JWT subject, which is a useful constraint, but it does not reveal other behavioral aspects: whether adding an existing item increases the quantity or creates a duplicate, what happens on failure, or any side effects beyond the implicit write operation.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is exceptionally concise, consisting of two sentences with no redundancy. It front-loads the primary action and follows with the key constraint, both of which are instantly actionable. Every word earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 8 parameters and no output schema, the description is thin. It does not cover how the system handles duplicate items, what happens when quantity exceeds limits, or how the cart is confirmed. The presence of a sibling tool like update_cart_item makes it crucial to clarify behavior when adding an already existing item, which is not addressed.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema provides descriptions for all 8 parameters, including the origin of item_id and the optional fields. The description adds minimal extra meaning beyond the schema, but even with full schema coverage, it does not explain the purpose of snapshot fields like title or unit_price in this context, which remains at baseline.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action (add a product to the authenticated user cart) and names the resource (cart). It is distinct from siblings like view_cart or update_cart_item, though it does not explicitly differentiate itself, making the purpose easily discernible.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description lacks guidance on when to use this tool versus alternatives. It mentions that the user ID comes from the JWT subject, but does not explain when to prefer add_to_cart over update_cart_item or how to handle existing cart entries. There is no mention of exclusions or alternative scenarios.

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

• search_productsB
  3.1/5.0
  Behavior2/5

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

  No annotations are provided, so the description must communicate behavioral traits, but it only states a basic search operation. It does not disclose pagination behavior via limit/offset, sorting choices, read-only safety, or any output characteristics. The description merely restates the tool's headline action without adding context.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single clean sentence with no filler, and the core purpose is front-loaded. It could benefit from slightly more structure or examples, but it remains appropriately concise and easy to parse.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given five parameters, no annotations, and no output schema, this one-line description leaves out important operational context: pagination semantics, sorting options, response shape, and how this search relates to sibling tools like get_product or get_categories. An agent must rely entirely on the schema and parameter names to understand calling conventions.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Input-schema descriptions already explain every parameter in detail (e.g., 'Words to search for', 'Number of products to return'). With 100% schema coverage, the baseline is 3, and the description does not meaningfully enhance parameter understanding beyond highlighting 'text query' and 'optional category'.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Clearly states the action ('Search'), the target ('the eBay catalog'), the result ('products'), and the primary filtering inputs ('text query' and 'optional category'). The verb–resource pairing is specific and easily distinguishes this from sibling tools like get_product (single product lookup) and get_categories.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Provides no guidance on when to use this tool versus the listed siblings (e.g., get_product for a known ID, get_categories for browsing). No exclusion conditions or alternative mentions are given, leaving the agent to infer usage from the general wording alone.

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

• get_orderB
  3.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral burden. It states the scoping constraint ('belonging to the authenticated user') but does not disclose what happens if the order is not found, whether the operation is read-only, or any authorization requirements. The verb 'Retrieve' implies a safe read, providing basic transparency without detail.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  A single, direct sentence with no filler. The key information (action, resource, ownership) is front-loaded and every word earns its place. Ideal conciseness for a simple retrieval tool.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's simplicity (one parameter, no output schema, no annotations), the description conveys the essential intent but lacks guidance on use cases and error behavior. It is minimally viable but leaves the agent to guess about return format and failure modes.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, and the order_id parameter is well-documented ('Order ID returned by place_order'). The tool description adds no additional parameter context beyond the schema, so a baseline of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('Retrieve') and resource ('one order'), and clarifies ownership ('belonging to the authenticated user'). It distinguishes from order_history by implying a single order fetch, though it does not explicitly mention lookup by ID. Clear enough for an agent to understand the core function.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  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 order_history or cancel_order. The description does not mention conditions such as needing an order_id from place_order, nor does it contrast with list operations. An agent must infer usage from the parameter schema alone.

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

• place_orderA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses the core side effects (placing the order and clearing the cart) and the requirement of an authenticated user. However, it does not mention what happens on failure (e.g., expired quote), permissions, or the return value, leaving some behavioral gaps.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  A single sentence that efficiently conveys the action, prerequisite, and side effect. Every word earns its place, and the most important information is front-loaded.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  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 no output schema, the description covers the essential action and side effects. However, it omits details about the response format, error conditions (e.g., expired checkout quote), and any post-conditions beyond clearing the cart. These gaps prevent a higher score.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema provides 100% coverage of parameters, including descriptions for checkout_id and shipping_address. The description adds context that the checkout quote must be unexpired, but it does not add meaningful semantics beyond what the schema already states. Baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses the specific verb 'Place' and names the resource 'authenticated user order', with a clear precondition ('from an unexpired checkout quote') and a distinct side effect ('clear the cart'). This clearly differentiates it from siblings like checkout, get_order, and cancel_order.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The phrase 'from an unexpired checkout quote' implies that the tool should be used after checkout and with a valid checkout_id. However, it does not explicitly state when to prefer this over alternatives, nor does it mention any exclusion conditions. The guidance is present but implicit.

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

• update_cart_itemA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral burden. It clearly discloses that setting quantity to 0 removes the item, which is a non-obvious side effect. However, it does not mention error conditions, whether the quantity overwrites an existing value, or any authentication requirements beyond the implied 'authenticated user'.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, concise sentence that front-loads the core action and includes the most important edge case (quantity 0). No filler or redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple two-parameter tool, the description covers the main intent and the removal edge case, but lacks information about failure modes, idempotency, or what happens when the item is not already in the cart. Given no annotations or output schema, a bit more context would be helpful, though the core usage is adequately clear.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the schema already documents both parameters. The description adds the 'authenticated user cart' context and reinforces the 0-removal behavior, but this largely mirrors the parameter descriptions rather than adding substantial new meaning.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('Set'), a clear resource ('item quantity in the authenticated user cart'), and a distinctive behavior (quantity 0 removes it). This cleanly separates it from sibling tools like add_to_cart and view_cart.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage context by mentioning 'authenticated user cart' and the update semantics, but it does not explicitly state when to prefer this tool over add_to_cart or view_cart, nor does it mention any exclusions or prerequisites beyond authentication.

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

• order_historyA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full behavioral burden. It discloses user scoping and sorting order, but does not explicitly state that this is a read-only operation or mention authentication requirements. It adds some value beyond the schema but lacks completeness.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, tightly written sentence that conveys the essential scope and ordering without any wasted words. It is front-loaded with the action and resource.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given two optional parameters and no output schema, the description covers the core purpose and constraints well. It lacks explicit return-format details and authentication prerequisites, but for a simple list operation, it is largely sufficient.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, providing descriptions for both 'limit' and 'status'. The tool description adds no parameter-specific information beyond what the schema already documents, so the baseline of 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb 'List' and resource 'orders' with clear scope ('belonging only to the authenticated user') and ordering ('newest first'). This distinguishes it from sibling tools like get_order (single order) and place_order (creating orders).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description clearly indicates this is a list operation scoped to the authenticated user, which implies use when retrieving order history. However, it does not explicitly state when to use this tool over get_order or how status filtering fits, leaving some inference to the agent.

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

• checkoutA
  3.9/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full transparency burden. It reveals the most important side effect boundary ('This does not place an order') and notes the quote is short-lived and uses live data. However, it does not explain whether the quote is saved, whether the operation modifies the cart, or what prerequisites are required (e.g., existing items). For a non-destructive preview tool, this is adequate but not thorough.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two concise sentences with no filler. It front-loads the core purpose and immediately includes the key limitation ('does not place an order'). Every word contributes to understanding the tool's role.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The definition is fairly complete for a simple one-parameter tool, but it lacks an output schema and does not describe what the returned quote contains, nor does it state whether a cart or items must exist before calling. Since the only parameter is well-documented in the schema, the main gaps are output format and usage prerequisites, making the description somewhat incomplete for confident invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema description coverage is 100%: the only parameter, shipping_address, is fully described ('Optional address used to calculate the checkout quote'). The tool description itself makes no mention of parameters, so it adds no semantic value beyond the schema. Baseline 3 applies because the schema already handles the meaning.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description clearly specifies the action ('create a short-lived checkout quote') using live eBay prices, and explicitly states what it does not do ('This does not place an order'). This disambiguates it from the sibling tool place_order, giving an agent a precise understanding of the tool's purpose.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives clear usage context: this tool is for previewing checkout with live prices, not for finalizing orders. It does not explicitly name the alternative tool (place_order) or specify prerequisites like 'items must be in the cart', but the 'does not place an order' statement provides a key exclusion that helps route an agent.

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

• cancel_orderA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It states the action and prerequisites, but does not mention side effects (e.g., order status changes to cancelled), error behavior for already-cancelled orders, or whether cancellation is reversible. This is a minimal viable description but not richly transparent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single concise sentence that front-loads the action and immediately follows with the key conditions. Every word earns its place, with no fluff or redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  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 no output schema, the description covers the essential context: who can use it and when it applies. It does not specify the resulting state or error handling, but these are less critical for a straightforward cancel operation. Overall, it is sufficiently complete for an agent to call the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema description coverage is 100%, so the parameter order_id is already documented as 'Order ID to cancel'. The description adds no additional semantics beyond restating the action. A baseline of 3 is appropriate because the schema already does the heavy lifting.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a clear verb ('Cancel') and resource ('an order'), and adds two important scoping conditions: it must belong to the authenticated user and must not already be cancelled. This distinguishes it from sibling tools like get_order or place_order, making the purpose unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear usage context: only cancel orders owned by the authenticated user and only when they are not already cancelled. It does not explicitly name alternatives or say when not to use this tool, but the conditions are sufficient for most agents to decide correctly.

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

• get_categoriesA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It clearly states this is a read-only retrieval operation, which is inherently safe. However, it does not disclose any behavioral traits such as error handling for invalid category_id, size limits, or response structure. For a simple read operation, this is acceptable but not rich.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single sentence, front-loaded with the action and resource, and every word contributes meaning. It is concise without losing necessary detail.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with one optional parameter and no output schema, the description covers the core call logic. It could specify what a subtree looks like or how invalid IDs are handled, but the low complexity and the schema's documentation of the parameter make this sufficiently complete for an agent to invoke the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% because the property description for category_id explains its meaning and the '0' special case. The tool description adds a subtle point about subtree behavior but does not materially go beyond the schema. This aligns with the baseline 3 for high schema coverage.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Retrieve') and names the exact resource ('eBay category tree'), including the optional subtree case. This clearly differentiates it from the sibling tools, which are all about products, cart, or orders—none deal with categories.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description makes the primary use case explicit: retrieve the full tree by default or a subtree when category_id is provided. It does not explicitly list when not to use it, but since there is no alternative category tool among siblings, this guidance is adequate. A small gap is not mentioning that omitting category_id is equivalent to 0.

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

• get_productA
  4/5.0
  Behavior3/5

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

  No annotations provided, so the description carries full burden. 'Retrieve' implies a read-only operation, and 'current details and pricing' indicates the data returned. However, it does not disclose potential errors, authentication requirements, or response structure. Acceptable for a simple lookup but not rich.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  A single, concise sentence that is easily front-loaded and contains no filler. Every word contributes to understanding the tool's purpose.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with one parameter and no nested objects, the description covers the core purpose. It lacks explicit mention of response format or error handling, but 'current details and pricing' hints at the output. Given the simplicity, the description is sufficient for agent invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The only parameter 'item_id' is fully described in the schema (100% coverage). The description adds no additional parameter meaning beyond the schema, so the baseline of 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  States a specific verb ('Retrieve'), a specific resource ('current details and pricing for one eBay item'), and scope ('one eBay item'). This clearly distinguishes it from sibling tools like search_products (searching) and get_categories (taxonomy).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies the tool is for fetching a single item's details, which is clear context. It does not explicitly mention when to use it over alternatives (e.g., after searching), but the single-item scope is enough guidance for selection.

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

• view_cartA
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the burden. 'View' implies a read-only operation and 'authenticated user' signals an auth requirement. It does not detail whether any side effects occur, but for a simple view operation that is likely unnecessary.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  A single, well-structured sentence. The verb and object are front-loaded, and every word adds meaning. There is no padding or repetition of the title.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a zero-parameter, read-only tool, the description is nearly complete. It identifies the resource and the key output (subtotal). It could perhaps mention that the full cart contents are returned, but the phrasing 'view the cart' implies this. Given the simplicity, no major gaps exist.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The tool has zero parameters, so the description needs to add no parameter-level meaning. The rule establishes a baseline of 4 when no parameters exist, and the description correctly focuses on behavior rather than params.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('View'), names the resource ('authenticated user cart'), and adds a concrete detail ('current item subtotal'). This clearly distinguishes it from sibling tools like update_cart_item or add_to_cart, which modify the cart, and order-related tools.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The context is clear: this tool is for viewing the current user's cart and subtotal. It does not explicitly state when not to use it or name alternative tools, but among siblings the intended use is unambiguous because no other tool reads the cart.

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