Checkout Page

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false. The description repeats 'Read-only' and adds that output comes as HTML and a React component, which is useful formatting context. It does not add behavioral details beyond the annotations, such as permission requirements or error behavior, so a baseline 3 is appropriate.

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 with zero waste: the first sentence front-loads what the tool returns, and the second provides precise usage context. Every sentence earns its place and the structure is easy to scan.

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

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

For a simple read-only code-generation tool with 100% schema coverage, full annotations, and an output schema, the description covers purpose and usage adequately. Return values are handled by the output schema, so the description does not need to explain them.

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 all three parameters, including the mode and pageType enums, are fully documented in the schema. The description adds no additional parameter meaning or usage constraints. Baseline 3 is correct when the schema does the heavy lifting.

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

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

The description states a specific verb and resource: 'Get ready-to-paste code that puts a checkout page, form, or event on a website.' It explicitly distinguishes the tool from sibling creation tools by naming create_checkout_page, create_form, and create_event as preceding actions. An agent can tell this is a code-generation/embed tool, not a creator or updater.

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

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

It gives clear triggering conditions: 'Use it right after create_checkout_page, create_form, or create_event when the user is building or editing a website, or when the user asks to add a checkout, buy button, ticket form, or signup form to their site.' This covers when to use it well. However, it does not name alternatives or explicitly state when not to use it, so it falls short of the top score.

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?

Goes well beyond the annotations by clarifying that destructiveHint=true is a soft archive: the group, ticket types, and sold tickets are retained, get_event still lists it with status archived, and can no longer be sold. It also discloses the non-obvious side effect that triggered ticket groups lose that trigger, and confirms the operation is reversible.

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

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

Front-loads the action and its effect, then layers retention semantics, side effects, and the reversal path in tight sentences. Every sentence adds information; nothing is redundant with the name or 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?

With annotations covering the safety profile and an output schema covering returns, the description supplies exactly the remaining context an agent needs: what is preserved, what changes for get_event, the trigger side effect, and how to undo it.

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 per-field descriptions and ID formats, so the schema already carries parameter meaning. The description only adds an ID-source hint, which is slightly at odds with the schema's stated source for pageId; baseline 3 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?

States a specific verb and resource (archive one ticket group on an event) and immediately names the observable effect: checkout no longer shows or sells it. This is clearly distinguishable from sibling update_ticket_group, which the description explicitly names as the reversal path.

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

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

Gives clear when-to-use context and an explicit alternative/reversal ('update_ticket_group with status enabled brings it back'), plus guidance that IDs come from get_event. Minor gap: it says event IDs come from get_event while the schema says pageId comes from list_events or create_event, so the sourcing hint is not fully consistent with the schema.

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?

It goes well beyond the annotations, which only say destructive=true and readOnly=false, by disclosing that data and sold tickets are preserved, that get_event still lists the type with status archived, and that dependent ticket types lose their trigger. These side-effect and reversibility details are exactly what a mutating tool needs to disclose.

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

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

Front-loaded with the core action and effect, then the non-obvious semantics (archived not deleted), then side effects, then ID sourcing. Every sentence carries distinct information and nothing is padded.

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 an output schema present, return values need not be explained, and the description covers purpose, persistence semantics, side effects, and parameter sourcing. Nothing an agent needs to invoke this correctly is missing.

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

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

Schema description coverage is 100%, so every parameter is already documented in the schema, including that IDs come from get_event. The description's line about sourcing IDs from get_event largely restates the schema rather than adding format or constraint detail, so the baseline of 3 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 gives a specific verb (archive) and resource (one ticket type on an event) plus the effect ('no longer on sale'), and explicitly distinguishes the action from deletion. An agent can tell this apart from update_ticket_type or a hypothetical delete without reading further.

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 states the operative condition (take a ticket type off sale) and tells the agent where to source all three IDs from get_event, which is real usage guidance. It stops short of naming alternatives or exclusions (e.g., when to prefer update_ticket_type instead of archiving), so it is clear context rather than full routing.

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?

Goes far beyond destructiveHint=true by enumerating concrete side effects: tickets issued, confirmation email with PDF, live-mode capacity decrement, booking.paid webhook, possible invoice generation, and no undo. The explicit non-idempotency warning and the full 409/403/400/429 guard list are exactly the kind of context annotations cannot carry.

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?

Bold headers and front-loaded warnings make it highly scannable. It is long, and some content (comp accounting, the 400 on dual strategy) is repeated between the prose and the examples, so it is dense rather than perfectly lean.

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 destructive, high-blast-radius mutation with 8 params and nested objects, nothing material is missing: prerequisites (Stripe connection, sale windows), conflict rules between parameters, error taxonomy, and duplicate-prevention guidance are all covered. An output schema exists, so return-value detail is correctly omitted.

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 would be 3, but the description adds real semantics: exactly one of paymentOption/complimentary must be supplied, couponId is rejected on comps, and each manualType maps to a distinct unpaid settlement flow. It also flags that `fields` must include the event's email field, which drives customer creation.

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?

Opens with a precise verb+resource+scope: 'Create a real event booking on an existing event, without collecting card payment.' It immediately distinguishes this tool from checkout-based creation ('that belongs on the event's own checkout') and from the read path (list_bookings), so an agent can route without consulting siblings.

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

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

Explicitly states when to use each of the two mutually exclusive strategies with concrete scenarios (box-office, invoiced corporate, comped speakers/press) plus three worked examples. It also gives negative guidance: no retry on uncertainty (use list_bookings instead) and no cancellation/refund/transfer through this API (use the dashboard).

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 this is a non-read-only, non-destructive creation tool, and the description adds material context beyond them: the page is created published and immediately live at a hosted URL, tax defaults to Stripe Tax, fields default to name/email/address, and omitting the required email field causes failure. It also explains side-effect semantics for disabled fields and supported payment-option combinations.

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 definition is long, but it is front-loaded with purpose and organized under Fields, Tax settings, Payment options, and Example uses, so an agent can scan to the relevant section. It loses a point for some repetition with the schema descriptions, particularly the tax-mode and payment-combination explanations that are restated in structured fields.

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 57 parameters, numerous nested pricing and field structures, and an output schema, the description covers the decisions an agent must make: defaults, constraints that cause failure, tax prerequisites, and the follow-up add_to_website step. It also names the return fields, which is useful for chaining even though the output schema exists.

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?

Although schema coverage is 72%, the description carries substantial meaning beyond the schema: it explains when to omit fields, the required email field constraint, the grouped address element versus flat fields, the three tax modes and their prerequisites, and the only supported payment-option combinations. The worked examples map natural language pricing requests directly onto productData.price / prices fields.

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

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

The opening sentence states a specific verb and resource ('Create a new checkout page with an attached product and pricing'), which lets an agent separate this from get_checkout_page, update_checkout_page, and list_checkout_pages without opening the schema. It also names what the page contains, so the scope is unambiguous.

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

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

Explicitly says to use it 'whenever a merchant wants to start accepting payments' and instructs a minimal page when the request is vague. It routes to concrete alternatives in the same ecosystem: list_theme_properties for design, list_themes for themeId, list_tax_rates/create_tax_rate for fixed tax, and add_to_website as the next step for website work.

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 only declare a non-read-only, non-destructive write, so the description must supply behavioral context — and it does: no matching rule means the code is accepted but discounts nothing, several rules on a page combine with OR, events cannot mix tickets and ticketsAndAddOns, and deprecated pageIds/ticketTypeIds are still accepted only without rules. That is genuine edge-case behavior an agent could not infer from annotations or schema.

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

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

The purpose and usage are front-loaded and the bold section headers aid scanning, but the middle bullet enumerating wholeOrder/prices/pricesAndBumps/tickets/ticketsAndAddOns reproduces the appliesTo enum description almost verbatim from the schema, adding length without new information. Roughly a third of the text is duplication of structured data.

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?

An output schema exists so return values needn't be described, annotations cover the safety profile, and the description covers the one genuinely hard part of this 14-parameter tool: how rules map pages, targets, and price/ticket/bump ids to actual discount behavior, including the empty-list and no-match 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 coverage is already 100%, so the schema carries the field documentation, but the description adds real semantics: exactly one of amountOff/percentOff, amountOff is shared equally across eligible lines and requires currency, and priceIds are the page product's price ids rather than Stripe ids. Some of this merely mirrors the schema's own prose, which keeps it from a 5.

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

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

States a specific verb and resource ('Create a coupon for Checkout Page') and immediately scopes it to the merchant creating a customer-entered discount code. It is unmistakable against siblings like list_coupons, update_coupon, and create_checkout_page, which are distinct resources or operations.

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

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

Gives a clear triggering condition: 'Use this when a merchant wants a discount code that customers can enter on eligible pages.' It does not, however, name the alternative (update_coupon) for modifying an existing coupon, nor state 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?

Beyond the annotations, the description discloses the creation output fields (data.id, data.name, data.hostedUrl, data.dashboardUrl) and instructs the agent to call add_to_website next without waiting for the user. This meaningfully explains the workflow and post-creation behavior of an open-world creation tool. The annotations already cover safety, and the description adds operational context.

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

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

The description is front-loaded with the core purpose and usage condition, followed by concrete examples and the required next step. Despite its length, every section adds useful guidance for a complex 60-parameter creation tool. It avoids repeating schema-only details in a wasteful way.

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 annotations, output schema, and complex nested ticket configuration, the description provides enough to select and invoke the tool correctly. It covers the purpose, primary data model, pricing/date formats, theme guidance, return values, and follow-up action. The remaining parameter details are left to the schema, which is appropriate.

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 adds useful meaning beyond the schema by explaining that an event contains ticket groups and ticket types, that prices are integers in the smallest currency unit, and that dates are ISO 8601. It also clarifies themeOverrides, hostedLayoutType, themeId, capacity, and ticket visibility rules with examples. With 60 parameters and only 53% schema description coverage, it still leaves many top-level parameters unmentioned, so it is strong but not comprehensive.

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

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

The description states a specific verb and resource: "Create a new event for selling tickets to an event." It also defines the event domain with ticket groups and ticket types, making the purpose clear. It does not explicitly name sibling tools such as create_checkout_page or create_form to sharpen the distinction, so it stops short of a 5.

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

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

It gives an explicit when-to-use condition: "Use this tool when a merchant wants to publish an event that sells tickets." It also prescribes the follow-up step through add_to_website when building a website. It does not explicitly state when not to use this tool or name update_event as the alternative for edits, leaving a small gap.

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 declare mutating, non-destructive, open-world behavior, but the description adds substantial context beyond them: that saving a layout rewrites every field's `order`, that visibility rules must reference persisted IDs from the page detail response (create-time keys are rejected), and that changing `reference` breaks exports/integrations. These are real operational consequences an agent could not derive from the schema or annotations alone.

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

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

Front-loads the core purpose and the mutating warning before the detailed layout mechanics. The ordering/layout passage is long and duplicates the schema's `order` text verbatim, costing some density, but no sentence is irrelevant to correct invocation.

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 25-parameter mutation with a full schema, output schema, and rich annotations, the description covers the genuinely subtle hazards: layout-driven reordering, ID requirements for visibility rules, integration-breaking `reference` changes, and the create-vs-update boundary. Only the omission of any mention of update_field keeps it short of 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 the baseline is 3, and most of the description's parameter explanation (the `order`/layout paragraph) is a near-verbatim repeat of the `order` schema description. It does add cross-tool framing by referencing `formLayout`, a page-level concept not present in this tool's schema, but overall it contributes little beyond the already-rich schema.

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

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

States a specific verb and resource ('Add one custom field to an existing checkout page, form, or event') and names the destination scope. It also distinguishes itself from the create_page tools by saying to pass fields to the create tool when building a new page, so an agent can tell it apart from create_checkout_page/create_form/create_event.

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 routes new-page field creation elsewhere ('to add fields on a new page, pass fields to the create tool instead') and explains when to use `order` versus `formLayout` for reordering. It never mentions the sibling update_field, leaving the create-vs-update choice to inference.

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 declare readOnlyHint=false and openWorldHint=true, so safety profile is partly covered; the description adds real behavioural context no annotation carries: the concrete return fields, and the mandatory follow-up with add_to_website that should not wait for the user. It omits permission/authorization requirements and publication state, keeping it below a 5.

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

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

Front-loaded with purpose and the minimal-request rule, followed by design pointers and the required follow-up step. Well organised, though the return-field list is partially redundant with the output schema and could be trimmed.

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 39-parameter creation tool with an output schema, the description supplies the missing workflow context (next step, minimal request, theme lookup) that the schema cannot. It stops short of discussing the formLayout/fields relationship and form-specific constraints, which is a modest gap 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 92%, so per-field documentation is already done. The description adds only light guidance, pointing agents at themeOverrides/hostedLayoutType, saying to consult list_theme_properties and list_themes for themeId. Useful cross-references, but most parameter meaning comes from the schema, so the baseline 3 holds.

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

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

States a specific verb and resource ('Create a new form page for lead capture or submissions') and frames the artifact's role, which separates it from create_checkout_page and create_event. The follow-up instruction naming add_to_website makes the tool's place in the workflow unambiguous.

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

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

Gives clear usage context ('when a merchant wants to publish a form...') and an explicit minimal-request policy plus when to add optional fields. It never explicitly excludes sibling alternatives such as create_checkout_page ('use that instead for payments'), so the routing guidance is strong but not fully comparative.

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=false and destructiveHint=false, so 'Mutating' adds little. Beyond that, the description doesn't cover whether re-adding a bump on the same page fails, what happens to existing bumps, or the returned resource — though the product eligibility constraints (currency match, single enabled non-plan price, not already offered) do add real behavioral context.

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

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

Three short sentences, front-loaded with purpose, then prerequisites, then mutation flag. No waste, though the trailing 'Mutating.' is largely redundant with annotations.

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 9 parameters (one nested object), full schema coverage, an output schema, and annotations, the description covers the essentials an agent needs: what gets created, where, its position, and the prerequisite product state. Missing only edge-case behavior for duplicate/failed creation.

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 nested showHideLogic is fully documented in-schema, so the baseline applies. The description only restates the product prerequisite, adding nothing about pageType/pageId selection or the show/hide rule that the schema doesn't already say.

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

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

Specific verb and resource (offer/create an order bump) with the exact scope (checkout page or event, shown as an add-on on events) and the ordering constraint ('added last'). An agent can distinguish it from update_order_bump, reorder_order_bumps, and create_product without opening schemas.

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 lays out the prerequisite path: create the product with create_product or find one with list_products (role: orderbump). It does not say when to prefer update_order_bump over creating a new bump, but the creation context is unambiguous.

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=false, destructiveHint=false and openWorldHint=false, so 'Mutating.' is largely redundant, but the description adds real value by disclosing scope (only order-bump products can be created standalone) and the required follow-up step with create_order_bump. It does not cover failure modes or what happens if the follow-up is skipped, so it stops short of a 5.

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

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

Three sentences, each load-bearing: what it creates, what to call next, and what it does not cover. The scope constraint is front-loaded before the sibling routing.

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 an output schema, full param coverage and annotations, the description only needs to establish scope and sequencing, which it does. The only residual gap is that it doesn't hint at the two required fields (role, title), though the schema marks them.

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% across 18 parameters, so the schema carries the semantics; the description only summarizes that title, price, image and card copy are set here. It adds no field-level guidance beyond that, which is the baseline expectation when the schema is this 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?

Opens with a specific verb and a narrow, precisely-qualified resource: 'Create an order bump product (`role: orderbump`)'. It immediately names what the product consists of (title, price, image, card copy) and explicitly excludes page products, so an agent can distinguish it from create_checkout_page/create_event without opening a schema.

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

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

Gives the full routing picture: use this for order bump products, use the page tools for page products, then call create_order_bump to actually offer it on a checkout page or event. Both the when and the when-not are stated with named 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 declare destructiveHint=true, openWorldHint=false and readOnlyHint=false. The description adds real behavioral context beyond that: the default-replacement side effect ('Only one tax rate can be the default at a time. Setting a new default replaces the previous one'), which explains WHY a create tool is flagged destructive. It does not discuss response shape, but the output schema covers that.

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

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

Front-loaded one-line purpose immediately followed by routing guidance, then bolded sub-sections for inclusive/exclusive, default, and the Stripe Tax distinction. Every section earns its place with 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?

An output schema exists so return values need no explanation, and annotations carry the safety profile. The description covers usage, the inclusive/exclusive semantics, and the default-replacement side effect, so an agent has everything needed to call it correctly.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema with a worked example ($100 with 20% inclusive tax = $83.33 + $16.67) and the default-rate selection behavior, extending the terse 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?

States a specific verb+resource ('Create a fixed tax rate for use on checkout pages') and the effect on the account. An agent can immediately tell this apart from read-only siblings like list_tax_rates.

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 when to use it (merchant wants a fixed percentage VAT/GST/Sales Tax on fixed-mode pages) and when NOT to, routing the agent to `tax.mode: "stripe"` for dynamic/address-based tax instead. Clear positive and negative 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 only declare the basic safety profile (non-readonly, non-destructive, closed-world). The description goes well beyond that: the baseThemeId copy includes order bump styling that only the dashboard can change, a copy of a built-in theme does not inherit the store's brand color unless tokens.colorPrimary is set, and omitted variable keys retain their values while null resets them. These are non-obvious side effects an agent could not infer from any structured field.

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

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

Three sentences, zero filler, front-loaded with the core action and then building outward to prerequisites and application. Every sentence carries distinct, actionable 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 3-parameter create tool with an output schema and full annotation coverage, the description supplies the creation workflow, dependency calls, and override semantics. Nothing an agent needs to invoke it correctly is missing.

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

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

Schema description coverage is 100%, so name, variables and baseThemeId are already well documented in the schema. The description mostly restates that documentation (the list_theme_properties pointer appears verbatim in both places) rather than adding new parameter syntax or constraints. Baseline 3 is appropriate when the schema carries the detail.

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

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

States a specific verb and resource ("Create a reusable theme") and immediately situates it in a workflow with named siblings (list_themes, list_theme_properties, create/update_checkout_page). An agent can distinguish this from update_theme or get_theme without opening any schema.

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

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

Gives concrete when-and-how: use baseThemeId from list_themes to inherit a design, then set deltas in variables, and call list_theme_properties for supported keys. It also explains where the result gets applied. It stops short of distinguishing this tool from the sibling update_theme, so the alternative routing is incomplete.

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=false, destructiveHint=false and openWorldHint=true, so safety is covered, and the description adds non-obvious behavioral facts: the operation is mutating and the new group is created empty. It does not discuss permissions, error cases or what the response contains, but the output schema exists, so this is a minor gap.

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

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

Three dense sentences, front-loading the action and its payload, then prerequisites, then the sibling alternative. No filler or restatement of the title.

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 20-param mutation with annotations and an output schema, the description supplies the essential workflow (event ID source, empty-group caveat, ticket-type follow-up, escaping to create_event). The remaining shortfall is the thin coverage of individual optional fields.

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 20 parameters at only 10% schema description coverage, the description must carry the semantics, yet it only name-drops broad groupings. Many inputs remain unexplained — status, reference, preselect, feeDisplay, layout internals, and the four hideWhen* booleans — so an agent still cannot tell what setting them does beyond their enum values.

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

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

Specific verb ("Add") plus resource ("one ticket group to an existing event"), and it enumerates the sub-concepts the group carries (capacity, sale window, availability trigger, selection type, discounts, display options). It also names the sibling it is not (create_event), so an agent can distinguish it without opening the schema.

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

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

Explicit routing is given: get the event ID from list_events, add the group's ticket types afterwards with create_ticket_type, and use create_event instead when creating an event together with its tickets. Conditions for the alternatives are stated, not inferred.

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=false and destructiveHint=false, so 'Mutating' adds little; the description does add that the tool attaches to an *existing* event and group, and explains the conditional-visibility semantics of showHideLogic. It says nothing about permissions, whether sale-window values are validated against the parent event, or what happens when capacity conflicts with the group.

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

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

Three tight sentences, front-loaded with the core action and scope before the ID-sourcing and alternative-tool guidance. No filler; the middle clause listing field families is dense but earns its space as a map of the payload.

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 27-parameter creation tool with sparse schema descriptions, the description gives almost no help on how to fill the payload. It does correctly defer return values (output schema exists), but an agent still cannot determine valid combinations such as availabilityBehavior plus triggerTicketTypeId from this text.

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?

27 parameters with only 15% schema description coverage, and the description only gestures at 'price, capacity, sale window, display options' without explaining the significant ones (availabilityBehavior's six modes, triggerTicketTypeId dependencies, pricing=paid/free/pwyw, min/maxQuantity, the six hideWhen* flags). It does meaningfully explain the showHideLogic comparison rule, but that single clarification does not compensate for the coverage gap.

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

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

States a specific verb and resource ('Add one ticket type to a ticket group on an existing event') and even enumerates the field families it accepts (name, price, capacity, sale window, display options, showHideLogic). This is clearly distinguishable from create_event (whole event) and create_ticket_group (the container).

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 routes the agent: get_event for the event and group IDs, create_ticket_group if a new group is needed, and create_event instead if the goal is a new event with tickets in one call. Both the prerequisite and the sibling alternative are named with their selecting conditions.

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 only declare the generic mutation profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), while the description adds substantial behavior: persistent account configuration requiring confirmation, the signing secret never being returned and being viewable only via the dashboard's actions menu, header auth being impossible here, and hard failure modes (10-webhook cap, duplicate URL). Nothing in the text contradicts the annotations.

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

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

Front-loaded with the happy path and then the hard constraints, with no filler sentences. It is longer than typical, but every paragraph addresses a distinct failure mode (missing URL, secret visibility, auth headers, limits), so the length is largely earned.

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?

An output schema exists, so return values need no explanation, yet the description still points at the meaningful response field (dashboardUrl) and the follow-up actions it enables. For a three-required-parameter write tool, the failure conditions and follow-up workflow for the receiving endpoint are fully covered.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds provenance semantics the schema cannot express: the url value must be user-supplied and must never be a placeholder, and header-related fields are intentionally absent. The events enum itself is left entirely to the schema, which 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?

Opens with a specific verb and resource ('Register an HTTPS endpoint that receives Checkout Page event notifications') and enumerates the event families it covers. It also explicitly distinguishes itself from the sibling update_webhook for re-pointing an existing endpoint, so an agent can route correctly without opening either schema.

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

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

Gives explicit preconditions and exclusions: the URL must come from the user, never be invented or reused, and if absent the agent must ask and wait. It adds a confirmation requirement before calling and names update_webhook as the alternative for changing an existing endpoint's URL.

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 and readOnlyHint=false, but the description still adds real context: permanence/irreversibility and the non-obvious fact that existing submissions retain their answers. It does not cover permission requirements or error behavior, so it falls just short of fully rich 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?

Three tight sentences with zero filler: the destructive scope leads, then the data-retention nuance, then the safer alternative. Every sentence carries distinct 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?

With an output schema present, return values need not be explained, and the description covers the remaining agent-facing needs: irreversibility, user confirmation, and the safer alternative path. Nothing material is missing for correct 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?

Schema description coverage is 100%, so all three parameters (pageId, fieldId, pageType) are already documented in the schema, including how to obtain fieldId and which pageType to use. The description adds no additional parameter-level meaning, so the baseline 3 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?

States a specific verb (delete) and resource (one custom field) plus the exact scope of page types it applies to (checkout page, form, event). The contrast with update_field makes it easy to distinguish from the adjacent mutation sibling without opening either schema.

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

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

Explicitly says when to use this (permanent removal) versus when to use an alternative (update_field with hidden: true when the field should just stop showing). It also instructs the agent to confirm with the user first, which is actionable routing 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 declare destructiveHint=true and readOnlyHint=false, but the description adds the non-obvious fact that the underlying product is NOT deleted, only the offering, and that it is recoverable via create_order_bump. It also instructs the agent to confirm with the user, which is real behavioral guidance beyond the raw flags.

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?

Four short sentences, front-loaded with the action and scope, followed by recovery, the preferred alternative, and the safety instruction. No filler.

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

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

An output schema exists so return values need not be described. For a destructive three-required-param mutation, the description covers scope, side effects, recovery, alternatives, and a confirmation requirement — nothing an agent needs is missing.

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

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

Schema description coverage is 100%, so pageId, pageType and productId are already fully documented in the schema, including the enum and ID patterns. The description explains the conceptual target (one page/one product) but adds no syntax or edge-case detail 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.

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

Specific verb ('Stop offering') plus resource ('an order bump') plus scope ('on one checkout page or event'). It is immediately distinguishable from create_order_bump, update_order_bump, and list_order_bumps.

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 names the preferred alternative for pausing ('Prefer update_order_bump with enabled: false') and the recovery path if the bump is needed again ('can be added again with create_order_bump'). That is when-to-use, when-not-to-use, and alternatives all in one place.

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 flag destructiveHint=true, but the description adds real value beyond them: irreversibility, the never-been-bought eligibility rule, the page-offering refusal behavior, and a user-confirmation requirement. These are operational constraints an agent cannot infer from the annotation block alone.

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

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

Three sentences with no filler: action and scope first, then refusal conditions, then the destructive/alternative guidance. Front-loaded in the order an agent needs to reason about safety before calling.

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 destructive tool with an output schema present (so return values need no explanation), the description covers eligibility, refusal behavior, parameter effect, irreversibility, and a safer alternative. Nothing material is left for the agent to guess.

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 both productId and fromAllPages are already fully documented, including the refusal-without-fromAllPages behavior. The description paraphrases the same fromAllPages semantics rather than adding format, default, or edge-case detail 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?

States a specific verb and resource ('permanently delete an order bump product') and immediately narrows scope with the eligibility constraint 'that has never been bought'. It also distinguishes itself from the similarly named delete_order_bump and update_product siblings by declaring what it will not touch ('Page products cannot be deleted here').

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

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

Gives explicit when-not conditions ('a product still offered on a page is refused unless fromAllPages is true', 'Page products cannot be deleted here') plus a named preferred alternative ('prefer update_order_bump with enabled: false to stop offering it'). The agent knows both the precondition for success and the softer option to route to instead.

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 and readOnlyHint=false, yet the description goes further by disclosing two concrete server-side failure modes (theme in use by pages, theme is store default), stating irreversibility, and requiring user confirmation. This is exactly the extra behavioral context annotations cannot carry.

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

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

Three short sentences, front-loaded with the action, then the failure conditions, then the safety instruction. No filler and no repetition of the title or annotations.

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?

An output schema exists, so return values need no explanation; the description instead covers the things the schema cannot: preconditions, irreversibility, and the confirmation requirement. Complete for a single-parameter destructive 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?

Only one parameter (themeId) and schema description coverage is 100%, with the pattern and sourcing ('as returned by list or create') documented in the schema itself. The description adds no format or sourcing detail beyond that, so the baseline 3 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?

States a specific verb+resource ('Delete a theme') and adds scope ('you created'), which cleanly distinguishes it from create_theme, update_theme, and get_theme in the sibling list. An agent can identify the operation without opening the schema.

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

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

Gives explicit preconditions for when the call succeeds or fails (pages in use, default theme) and prescribes the remedy (move pages first) plus a user-confirmation step. It does not name a sibling alternative, but for a delete there is effectively none, so this is strong context without formal exclusions.

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 and readOnlyHint=false, so the safety profile is known. The description still adds real behavioral detail beyond that: deliveries cease immediately, the endpoint vanishes from list_webhooks, and delivery history is retained — the last being a non-obvious side effect an agent would otherwise have to guess. "Irreversible" mildly restates the destructive hint, keeping this just short of 5.

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?

Four short sentences, front-loaded with purpose and followed by effects, then the safety instruction. Nothing is padding, though "Destructive and irreversible" overlaps partly with the destructiveHint annotation rather than adding fully new 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 destructive one-parameter mutation, the description covers side effects, retained data, irreversibility, and the lookup/confirmation workflow. An output schema exists, so return values need not be explained, and nothing an agent needs before calling is missing.

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

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

Schema coverage is 100% and the pattern plus "as returned by create or list" already documents the single webhookId parameter. The description only reinforces where to obtain the id, so the baseline of 3 is appropriate — the schema carries the load.

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

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

States a specific verb and resource ("Delete a webhook endpoint by id"), which immediately separates it from siblings like delete_product or update_webhook. The scope (single endpoint identified by id) is unambiguous.

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

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

Explicitly routes the agent to list_webhooks to obtain the id, and adds a procedural prerequisite to confirm with the user before invoking. This is both when-to-use guidance and an invocation precondition rather than vague 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?

Despite annotations already marking the tool read-only, the description adds substantial behavioral context: 404 behavior for missing bookings, test-mode semantics via `livemode`, caveats that ticket capacities are historical snapshots, complimentary-booking semantics, and archived-booking semantics. It also clarifies that mutations must happen in the dashboard, matching the read-only 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 purpose is front-loaded, followed by alternatives, error behavior, field caveats, examples, and mutation limitations in a logical order. The extra detail is dense but warranted for a booking retrieval tool with non-obvious data semantics.

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 annotations, a complete input schema, and an output schema, the description covers the remaining behavioral gaps an agent needs: when to use it, test-mode handling, missing-ID behavior, and misleading field caveats such as historical capacity snapshots. Nothing essential for correct invocation is missing.

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

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

Schema description coverage is 100%, so both parameters are already well documented in the input schema. The description reinforces `livemode` test-mode behavior and booking ID discovery via `list_bookings`, but it does not add much parameter-specific detail beyond what the schema already provides.

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

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

The description states a specific verb and resource: retrieve a single event booking by ID from a Checkout Page account. It also distinguishes this tool from `list_bookings` and `list_payments`, so an agent can select it confidently among siblings.

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

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

It explicitly says to use `list_bookings` first when discovering a booking ID by customer email, name, event title, or order ID, and directs checkout payment lookups to `list_payments`. This gives clear when-to-use and when-to-use-an-alternative 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 declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuine behavioral detail beyond that: the exact 404 error string on a missing ID, and the kinds of configuration visible on the page (draft/published/archived status, product, files, images, redirects).

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 core purpose and the guard on ID-based lookup are front-loaded in the first two paragraphs. The four-item example list is a bit padded, but each example maps to a plausibly distinct agent intent rather than restating the same operation.

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

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

For a single-parameter read tool with an output schema, the definition covers purpose, precondition (known ID), sibling routing, and error behavior. Nothing needed to invoke it correctly is missing; return shape is appropriately left to the 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 the pageId property already documents the 24-hex pattern and where to obtain the ID. The description still adds value by tying the ID source to create_checkout_page's returned id and by stating the failure behavior for an unknown ID.

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

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

The description opens with a specific verb and resource ("Retrieve a single checkout page by ID") and scopes it to an account. It is clearly distinguishable from siblings like list_checkout_pages, create_checkout_page, and update_checkout_page.

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 names the condition for use ("when you already know the checkout page ID and want to inspect the current configuration") and explicitly routes create flows to create_checkout_page, including the post-create lookup pattern. The example utterances reinforce the when-to-use boundary.

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 cover the read-only/non-destructive profile, and the description adds substantial context beyond them: the 404 error text for missing IDs, no pagination, the identity-only scope (no purchase history), the non-overlapping transaction tools, and that deletion requires human intervention in the dashboard.

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?

Well front-loaded with purpose and routing, but bloated and repetitive: the dashboard/portal edit path and the GDPR deletion requirement each appear twice (once in the body, once under 'Example customer support uses'). Multiple example sections restate the same 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 an output schema exists, return values needn't be explained, yet the description still covers the billing vs. shipping address distinction, identity-only scope, and routing to transaction tools. Nothing an agent needs to call it correctly is missing.

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

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

Schema coverage is 100% with a documented pattern and the 'use list_customers first' hint already in the schema, so the description largely repeats the schema's ID semantics. Baseline 3 is appropriate since the schema does the heavy lifting for the single parameter.

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

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

States a specific verb and resource ('Retrieve a single customer by ID') and immediately scopes it ('without pagination', 'one customer record directly by ID'). It explicitly distinguishes itself from the sibling list_customers by clarifying that it is for when you already have the ID.

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?

Names the alternative (list_customers) and the exact condition that selects it (discovering an ID by email/name), and adds cross-tool routing to list_payments/list_bookings/list_subscriptions with the customerId filter. It also states when-not behavior (ID not found returns 404).

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 and openWorldHint=false, so safety and scope are covered. The description adds workflow sequencing and that the full configuration is returned, but says nothing about authorization requirements, error behavior for a missing/invalid id, or pagination/size, so the added context is modest.

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 compact sentences with zero waste: the retrieval behavior is front-loaded, then the workflow guidance. Nothing is repeated from the schema or annotations.

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?

An output schema exists, so return-value detail is unnecessary, and the single required param is fully documented. The only gap is not pointing at list_events as the alternative for enumerating multiple event pages, which would have rounded out the routing 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?

Only one parameter, and the schema documents it at 100% coverage including the 24-hex pattern and an example. The description still adds meaning by explaining where the id typically comes from (create_event's returned id), which is not in the schema.

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

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

States a specific verb and resource — 'Retrieve a single event page and its full configuration by ID' — which also implicitly contrasts with list_events by emphasizing 'single'. It names create_event and update_event, but as workflow partners rather than as alternatives it is being distinguished from, so the sibling differentiation is partial.

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

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

Gives clear situational context: use the id returned by create_event for a direct lookup, or call this before a partial update with update_event. It does not say when to prefer list_events instead of a direct fetch, but the when-to-use guidance that is present is concrete.

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 destructiveHint=false, so the safety profile is covered. The description still adds real value beyond that: the exact 404 message on a missing ID, and the surface of what can be inspected (status, fields, files, images, redirects). It stops short of describing what the response payload looks like, but an output schema exists to cover that.

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?

Purpose and precondition lead, alternatives follow, and the example list at the end is skimmable rather than buried. The four bullet examples are slightly redundant with the prose but each illustrates a distinct query intent, so little is wasted.

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

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

For a single-parameter read tool with annotations covering safety and an output schema covering the return shape, the description supplies the remaining gaps: precondition, sibling routing, and error behavior. The only omission of note is any rate-limit or pagination nuance, which is negligible here.

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

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

Schema description coverage is 100%, so the pageId pattern and provenance are already documented in the schema. The description adds only the 404 consequence of passing an unknown ID and the pointer to use the page `id` returned from create_form — useful but marginal against a fully documented parameter.

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 first sentence states a specific verb and resource — 'Retrieve a single form by ID from your Checkout Page account' — which unambiguously separates it from list_forms. The scope ('single', 'by ID') and the object ('form') are stated up front with no hedging.

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

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

It gives an explicit precondition ('when you already know the form ID'), names the alternative tool for the other case ('For create flows, use create_form'), and even describes the post-creation lookup path. Both the when-to-use and the sibling routing are spelled out.

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 only cover the read-only safety profile; the description goes further, disclosing that responses carry a freshly signed link, that the link expires one hour after the response, that it is safe to share with the buyer, and how to reach test-mode records. That is substantive behavioral context the annotations do not 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?

Four tight sentences, front-loaded with the core action and ending with the sibling routing. The `livemode` sentence mildly duplicates the schema description, but nothing is padded.

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 only two params, full schema coverage, an output schema, and annotations, the description supplies exactly the missing pieces: link freshness/expiry and sharing safety. Nothing an agent needs to call or interpret this tool is absent.

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 `id` and `livemode` are already fully documented. The description's `livemode: false` note and id-discovery hint restate the schema rather than adding syntax or format meaning, so the baseline 3 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?

States a specific verb and resource ("Retrieve a single invoice by id") and immediately contrasts with list_invoices for discovery. An agent can distinguish it from get_payment, get_customer, and list_invoices without opening any schema.

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

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

Explicitly routes: use `list_invoices` first to discover an id by customer, invoice number, PO number, or chargeId, and names `regenerate_invoice` for rebuilding the PDF. Both the when-to-use and the alternative are stated rather than inferred.

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 destructiveHint=false, and the description reinforces that with a named side-effect exclusion (refunds/cancellations). Beyond annotations it adds concrete error behavior (404 "Payment not found" when the ID isn't owned by the authenticated seller) and the livemode test-data toggle. It doesn't describe pagination or response shape, but an output schema exists.

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

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

Front-loads purpose and routing in the first two paragraphs, then errors, examples, and constraints. The example-uses block and the livemode sentence are mildly redundant given the schema and output schema, but nothing is bloated or buried.

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?

Combines a simple 2-param retrieval, a rich schema, and an output schema, and the description still covers the missing pieces an agent needs: cross-sell to list_payments, bookings exclusion, 404 semantics, and read-only scope. Nothing required to call it correctly is absent.

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 both parameters are already fully documented, including the livemode test-mode meaning and the paymentId pattern/'list first' hint. The description's "Pass livemode: false to read test-mode records" mostly restates the schema rather than adding new semantics, so the baseline 3 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?

States a specific verb and resource ("Retrieve a single payment by ID") and scopes it to the Checkout Page account. It also explicitly separates itself from list_payments and from event bookings, so an agent can distinguish it from the many get_* siblings without opening any schema.

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

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

Gives explicit when-to-use routing: "Use list_payments first if you need to discover a payment ID by customer email, customer name, product title, or order ID," and redirects event bookings to list_bookings. It also names what can't be done here (refunds/cancellations) and points to the dashboard.

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, and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context by enumerating the product data included and clarifying the ID provenance, though it does not describe not-found behavior or auth requirements.

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 waste: the retrieval scope and returned fields come first, followed by the ID provenance note. It is appropriately sized and front-loaded.

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-resource read tool with full schema coverage, clear annotations, and an output schema, the description provides everything needed to understand scope and invocation. Return-value details are rightly left to the 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 description coverage is 100%, and the single productId parameter is fully documented in the schema with its pattern and source. The description reinforces the ID source but does not add format or semantic details beyond what the schema already provides, so 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 states a specific verb and resource: "Retrieve a single product by ID," and lists the data returned (prices, variants, stock, tax, file settings). This clearly distinguishes it from siblings like list_products and update_product without needing the schema.

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

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

The description implies when to use the tool by saying it retrieves a single product by ID, and it explains where to find that ID via get_checkout_page. However, it does not explicitly compare against alternatives such as list_products or state when not to use it, leaving guidance at an implied level.

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, and openWorldHint=false, yet the description still adds real behavior: the 404 "Submission not found" outcome, the absence of pagination, and the livemode/test-mode switch semantics. It also confirms the write boundary and points to the dashboard as the alternative, which prevents an agent from attempting unsupported edits.

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

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

Front-loaded with the core action and scope, followed by the routing rule and the read-only boundary. The four example utterances are somewhat redundant given the usage paragraph, but they are short and help match colloquial user requests. Slight over-length keeps it off a 5.

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?

An output schema exists, so return values needn't be spelled out, and the description correctly focuses on scope, error behavior, and the read-only constraint. Nothing an agent needs to call this correctly – ID format expectations, test vs live selection, missing-record behavior – is absent.

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% – both `submissionId` (with its 24-hex pattern and list-first hint) and `livemode` are fully documented in the schema. The description restates the livemode test-mode behavior and the list-first advice, which reinforces rather than adds new semantics. Baseline 3 is correct where the schema already carries the load.

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

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

States a specific verb and resource ("Retrieve a single form submission by ID") plus the account scope ("your Checkout Page account"). It also names the sibling `list_submissions` and clearly delineates that this tool is the ID-based single-record fetch, so an agent can distinguish it without opening a schema.

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

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

Explicitly tells the agent to call `list_submissions` first to discover an ID by email, name, page, customer ID, or date range. It also gives the when-not path: modification requests cannot be done here and must be handled in the Checkout Page dashboard.

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, but the description adds the 404 'Subscription not found' behavior when the ID doesn't belong to the authenticated seller, plus the livemode test-vs-live data scoping. The read-only restatement is redundant with the annotation and the tool doesn't mention pagination or response size, so it stops short of a 5.

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

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

Front-loaded with purpose, then guidance, then error behavior, then a short example block — easy to scan. Minor waste: 'This tool is read-only' restates the annotation and the hint to use list_subscriptions appears both in prose and in the parameter description.

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 2-parameter read tool with an output schema, the description covers the lookup pattern, the test/live mode switch, the failure mode, and the adjacent tools for discovery and cancellation. Nothing an agent needs to call this correctly is missing.

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

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

Schema coverage is 100% and both parameters are documented in the schema, including the ID pattern and the livemode default. The description only reinforces the list_subscriptions discovery path, adding little beyond what the schema already says, so the baseline 3 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?

Opens with a specific verb+resource+scope: 'Retrieve a single subscription by ID from your Checkout Page account.' This immediately distinguishes it from the sibling list_subscriptions and from get_subscription_payment or prepare_subscription_cancellation.

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 routes the agent: use list_subscriptions to discover an ID by email/name/product/order, and use prepare_subscription_cancellation for cancellation context. It also names the out-of-scope operations (cancellation, refunds) that must be done in the dashboard, which is a genuine when-not rule.

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 destructiveHint=false, so the description isn't carrying the safety burden — yet it still adds real behavior: a 404 with the exact message when the ID doesn't exist for the authenticated seller, test-mode access via livemode:false, and the constraint that refunds cannot be done here (dashboard only). It doesn't discuss rate limits or auth requirements beyond the seller scoping, keeping it just short of a 5.

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

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

Front-loaded with purpose and scope, then grouped under clear bold headers for error behavior, status fields, and examples. It is on the long side and the three example utterances plus the restated read-only line are marginal, but nearly every sentence carries distinct 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?

An output schema exists, so return values need no explanation, yet the description still flags the two independent status fields (paymentStatus vs. invoiceStatus) and that both must be checked when answering 'did this payment go through?' — exactly the kind of domain trap an agent would otherwise get wrong.

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 both parameters are already documented in the schema, including the exact livemode test-mode semantics and the 'not the subscription it belongs to' warning on subscriptionPaymentId. The description largely repeats this, so the baseline 3 applies; it adds no format or syntax detail beyond the schema.

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

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

States a specific verb and resource ('Retrieve a single subscription payment by ID') and immediately carves out scope: 'one charge within a subscription's billing cycle, not the subscription itself.' An agent can distinguish it from get_subscription and get_payment without opening any schema.

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

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

Explicitly routes to alternatives by name and condition: use `list_subscription_payments` first to discover an ID (filtered by `subscriptionId`), and use `get_subscription` for subscription-level status/schedule/next-billing-date. Both the when-to-use and the when-not-to-use cases are stated.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description's 'Read-only' merely restates that. It does add that the returned theme includes its design settings via `variables`, but says nothing about auth needs, error behavior, or whether a missing id returns empty vs. an error.

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

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

Two short sentences, resource and payload front-loaded, no filler. Minor waste in the trailing 'Read-only.' which duplicates the readOnlyHint annotation.

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

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

For a single-param read tool with an output schema, the description covers what an agent needs to invoke it: what is fetched and what it contains. The absence of sibling differentiation and error/id-origin context keeps it from a 5.

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?

Only one parameter and schema coverage is 100% (themeId documented in the schema, including the 24-hex-char pattern and origin 'as returned by list or create'). The description adds no meaning beyond the schema, so the baseline 3 for schema-carried params is correct.

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

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

States a specific verb (Fetch) and resource (one theme by id) and names the key payload field (`variables` = design settings). It implicitly separates itself from list_themes and list_theme_properties, but never explicitly contrasts with those siblings, so it falls just short of a 5.

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

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

There is no when-to-use guidance: nothing tells the agent to prefer this over list_themes or list_theme_properties, nor that a theme id must come from list_themes/create_theme (that hint lives in the schema, not the description). Usage is only inferable from the phrase 'by id'.

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 destructiveHint=false, so the closing "Read-only." is redundant. However, the description adds genuinely new behavior with annotations absent: the signing secret is never returned, custom header values are redacted as `[hidden]`, and headers must be managed via the returned `dashboardUrl`. That redaction disclosure is the kind of thing an agent cannot infer from structured fields.

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

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

Three short sentences, front-loaded with purpose, then the redaction caveat, then the sibling pointer. Nothing padding; even the somewhat redundant "Read-only" is a single clause.

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 an output schema present, the description needn't enumerate return values, and it correctly focuses on the surprises an agent would hit (hidden secret, masked headers). What's missing is minor: error behavior for a not-found or malformed id, and confirmation of what `status` values mean.

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 the single parameter already documents the 24-hex format and its origin. The description only restates the id concept and cross-references list_webhooks, so it adds little parameter-level meaning 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?

Specific verb and resource ("Fetch one webhook by id") immediately followed by the fields returned (URL, subscribed events, status, delivery counters). It is clearly distinguished from the sibling list_webhooks, and even from update_webhook by noting that editing happens elsewhere.

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

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

Gives a concrete prerequisite path: "Use list_webhooks to find the id." That is enough for an agent to route correctly between single-fetch and list. It stops short of stating when *not* to call it (e.g., bulk inspection, or which sibling to use for secret rotation), so it is not a full 5.

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, openWorldHint=false, and destructiveHint=false, and the description adds substantial complementary context: it explicitly says the tool is read-only and cannot modify, transfer, cancel, or refund. It also discloses data limitations around refund history, email delivery, cancellations, address fields, and inventory snapshots.

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

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

The description is well structured and front-loaded, with clear headings and practical examples. However, it is extremely long for a single tool definition, and some passages could be tightened without losing needed 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 the tool's 16 optional filters, multiple status fields, pagination, and many support-question edge cases, the description is complete enough for an agent to invoke it correctly. An output schema exists, so the description does not need to explain return values, but it still adds useful interpretation guidance for key fields.

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

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

Schema coverage is 100%, so the baseline would be 3, but the description adds important semantic guidance beyond the schema. It explains the independence of status, orderStatus, isComplimentary, and archivedAt; the meaning of date filters in UTC; cursor pagination behavior; and practical limit choices.

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

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

The opening sentence states a specific verb and resource: retrieve a paginated list of event bookings from a Checkout Page account. It also distinguishes the record set from payments and subscriptions later in the description, so an agent can tell what this tool is and is not.

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 gives extensive when-to-use guidance with concrete support examples, filter recommendations, and explicit alternatives. It routes order lookups to list_payments/list_subscriptions when needed and directs full customer history across all three transaction 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, destructiveHint=false and openWorldHint=false, so the description only needs to add context, which it does: newest-first ordering, full configuration included in results, and archived pages omitted by default. It stops short of describing pagination semantics or result shape, but the output schema and annotations cover those.

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?

Four sentences, each carrying a distinct purpose: scope, archived default, ID-finding role, and sibling routing. Front-loaded with the core action and no wasted clauses.

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 annotations covering safety, an output schema covering return values, and 100% schema coverage for parameters, the description fills its remaining role: ordering, default filtering behavior, and sibling disambiguation. Nothing an agent needs to invoke it correctly is missing.

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

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

Schema coverage is 100%, so all six parameters are already documented with enums, defaults and cursor constraints. The description reinforces the status/archived default but adds no syntax or format detail beyond what the schema provides, making the baseline 3 correct.

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

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

States a specific verb and resource ('List the checkout pages'), plus scope ('newest first, each with its full configuration, product and fields'). It explicitly names what it is not (forms and events are separate page types) and distinguishes itself from get_checkout_page/update_checkout_page.

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

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

Gives explicit routing: use this to find a page id for get_checkout_page and update_checkout_page, and use list_forms/list_events for the other page types. It also explains the default status behavior (archived excluded unless filtered), which is exactly the condition an agent needs to decide whether to pass 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?

Beyond the readOnlyHint/destructiveHint annotations, it discloses that soft-deleted coupons are returned, that there is no single 'active' flag (deleted/redeemBy/maxRedemptions must be combined), that results are newest-first, that discount fields are immutable after creation, and that there are no server-side filters beyond search. This is substantially more than the annotations carry.

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

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

The description is front-loaded and well-sectioned with bold headers, and nearly every sentence is substantive. However, the 'Reading a coupon' and 'Scoping' sections explain return-value fields in depth even though an output schema exists, which is more length than the tool strictly requires. Dense and organized, but longer than necessary.

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 4-parameter, read-only list tool with full schema coverage and an output schema, the description covers purpose, alternatives, filtering limits, pagination, and the semantics an agent needs to interpret results correctly. Nothing material is left to inference.

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