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

Beyond the destructiveHint annotation, the description reveals that cancellation is irreversible, runs as a background task returning a job id rather than the updated order, and may fail with userErrors for fulfilled orders. It also discloses that cancellation cannot be undone and has no partial-return capability. This is rich behavioral context that annotations alone 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?

The description is compact, front-loaded with the most critical fact (irreversible), and every sentence carries essential operational or behavioral information. There is no filler or repetition of obvious schema details.

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

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

With no output schema, the description properly explains the asynchronous job response and directs the agent to verify via get_order. It covers required decisions, customer notification, failure modes, and unsupported scenarios. For a destructive tool with six parameters, this is a complete and actionable description.

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 value by highlighting that refund and restock are mandatory decisions with no defaults, and that notifyCustomer controls the customer email. This goes beyond simply restating the 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?

Description opens with 'НЕОБРАТИМО отменяет заказ' — a specific verb and resource that clearly identifies the action. It further distinguishes itself from sibling read tools like get_order by focusing on the irreversible mutation, and from any partial-refund tool by explicitly stating partial returns are not supported.

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 clear usage context: both refund and restock decisions are mandatory, cancellation is asynchronous, and the result must be verified via get_order. It also states exclusions — fulfilled orders cannot be cancelled and partial returns are not possible — though it does not explicitly name an alternative tool for those cases.

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 (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true), the description discloses meaningful behavioral traits: startsAt defaults to now so the code activates immediately, a repeat call with the same code fails via userErrors because codes must be unique, and only one of percentage/amount is accepted. These failure modes and default behaviors are exactly what an agent needs to anticipate outcomes. The description is consistent with the annotations — no contradiction.

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

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

Four dense sentences with a logical progression: what is created and its constraints, default timing, limit semantics, then boundaries and failure mode. Every sentence earns its place and the core purpose is front-loaded. It is on the longer side, and the usageLimit/appliesOncePerCustomer sentence partially duplicates the schema descriptions, but there is no filler or repetition.

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

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

For an 8-parameter mutation tool with no output schema, the description covers the essential operational context: scope, exclusivity constraint, default behavior, failure mode (userErrors on duplicate code), and scope boundaries. The main gap is that it does not describe the success return value or shape; however, the userErrors mention hints at the response contract, and the failure disclosure is the more critical information 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 the baseline is 3. The description adds value beyond the schema by elevating the mutual-exclusivity constraint between percentage and amount to a top-level rule, giving a concrete interpretation example (0.2 = −20%), and clarifying that an omitted startsAt means immediate activation. The mentions of usageLimit and appliesOncePerCustomer largely paraphrase the schema, but the exclusivity and timing semantics are genuine additions.

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+resource — 'Создаёт базовую промокодную скидку' (creates a basic promo-code discount) — and then precisely defines the boundaries of 'basic': one code, all customers, all products, with exactly one of percentage/amount. It distinguishes itself from the sibling graphql_request by explicitly listing what this tool does NOT create (collection/segment discounts, BXGY, free shipping, disabling discounts), so an agent can disambiguate without inspecting other tools.

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

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

The description explicitly states when not to use this tool and names the alternative: discounts on individual collections/segments, BXGY, free shipping, and disabling a discount are not created here — for those, use graphql_request. It also states the hard usage rule 'ровно одно из двух' (exactly one of percentage/amount) and the uniqueness constraint, leaving no ambiguity about preconditions or 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?

Beyond the annotations, the description discloses substantial behavioral traits: products are not published to any sales channel, ACTIVE status does not mean published, DRAFT marks a draft, failures come as userErrors with HTTP 200, and the default variant is included in the response. None of this 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?

The description is dense but every sentence adds critical operational knowledge. It front-loads the core behavior and then systematically covers publication, status, pricing, limitations, idempotency, and error handling with no wasted words.

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

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

For a create operation with no output schema, the description covers all essential context: what is returned, how to proceed with pricing, how to publish, what is not created, duplicate behavior, and the unusual HTTP 200 error pattern. An agent has enough information to invoke the tool correctly and handle next steps.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds meaningful semantics beyond the schema, especially around status: ACTIVE is default but still unpublished, and DRAFT additionally marks the product as a draft. It also clarifies that the price is not set through this call but via a subsequent update_variant call.

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

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

The description clearly states the tool creates a product and returns it with the default Shopify-created variant. It also explicitly separates this tool from related operations by noting it does not publish, set prices, or create variants/images/inventory, which distinguishes it from siblings like update_variant and graphql_request.

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 explicit when-not-to-use and alternative guidance: publishing must be done via graphql_request, pricing via update_variant, and variants/images/stock are not handled here. It also warns that repeated calls create duplicate products, which is critical usage context.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds meaningful behavioral context beyond those: what exact data is returned (including the 10 orders), accepted identifier formats, and the non-error behavior for non-existent customers (data: null). This fully discloses the operational traits an agent needs.

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 two well-structured sentences. The first sentence fronts the primary return value; the second covers input formats and an important edge case. Every clause earns its place, and there is no redundant filler.

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

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

For a single-parameter read-only tool, the description is complete: it specifies the resource, the response contents, accepted input formats, the null behavior for missing entities, and directs email lookups elsewhere. No output schema exists, but the description adequately covers the return shape. Annotations cover safety and idempotence. Nothing critical 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 the baseline is 3. The description essentially repeats the schema's id format ('numeric id or gid://shopify/Customer/<id>') without adding new parameter-level meaning. The email routing comment is usage guidance rather than parameter semantics, so no credit above baseline is warranted.

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

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

The description clearly states a specific verb and resource: returns a single customer with a defined set of fields (contacts, addresses, note, tags, last 10 orders). It distinguishes itself from list_customers by explicitly noting that email-based lookup belongs to that sibling. The purpose is immediately recognizable and 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?

The description provides explicit usage guidance: use this tool for fetching by numeric id or gid, and route email lookups to list_customers with a specific query format. This gives the agent clear conditions for selecting the correct tool among siblings and excludes a common misinvocation pattern.

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, openWorldHint, idempotentHint, and destructiveHint=false. The description goes beyond these by disclosing that a non-existent order returns data:null rather than an error, and that item lists are capped at 100 entries. These are meaningful behavioral facts not captured by 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 description is one dense paragraph with every sentence carrying essential information: return contents, accepted id forms, the #1001 distinction with a routing instruction, and the not-found behavior. Nothing is redundant or 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?

With one parameter fully documented in the schema, no output schema to rely on, and annotations covering the safety profile, the description provides the needed return-shape details, id-format nuance, and error semantics. An agent has everything necessary to invoke and interpret this tool correctly.

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

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

The schema already provides 100% coverage for the single id parameter, including the exact same guidance about numeric id vs gid:// vs #1001. The description repeats this but does not add additional parameter-level semantics beyond what the schema already states, so it stays at the baseline for full schema coverage.

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: returns one complete order. It enumerates the concrete contents (items, totals, address, note, tags, shipments with tracking numbers), which makes the tool's scope immediately clear and distinguishes it from list_orders and other sibling tools.

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

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

The description explicitly explains when this tool is appropriate, including the id format accepted, and directly routes the agent to list_orders with query "name:#1001" when only the order number is available. This is clear usage guidance with an explicit alternative.

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

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

Annotations already mark this as read-only, idempotent, and non-destructive, but the description adds valuable non-obvious behavior: a non-existent product returns data: null rather than an error, the response caps at 100 variants, and media/metafields are deliberately excluded. This goes well beyond the annotations and helps the agent set correct expectations.

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 with no filler: the main return contents are front-loaded, followed by id format, null behavior, and exclusions. Every sentence adds necessary 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 single-product read tool with no output schema, the description is complete enough to invoke safely: it covers return contents, limits, id formats, error semantics, and what to use instead for missing data. No critical operational detail 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?

The input schema already fully documents the single id parameter, including that it can be a numeric id or a gid://shopify/Product/<id>. The description does not add new parameter meaning beyond restating what the schema provides, so schema coverage carries the weight.

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

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

The description uses a specific verb and resource ('Возвращает один товар целиком') and clearly enumerates what is included: description HTML, options, up to 100 variants with prices, stock, SKUs, and inventoryItem id. It also differentiates itself from list_products by focusing on a single full product, and explicitly says media/metafields are not returned.

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 clearly implies this is the tool to fetch one complete product, and it gives an explicit exclusion: media files and metafields are not returned, and for those the agent should use graphql_request. It does not explicitly contrast with list_products, but the single-item scope and the alternative routing for omitted data provide solid usage 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 the tool read-only, idempotent, and non-destructive. The description adds useful behavior beyond that: the shop is fixed by an environment variable, and every response includes GraphQL cost-bucket details with field-level explanations. This gives the agent a clear model of what to expect.

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 main return value and its fields, then explains input constraints, then covers the shared cost-bucket behavior. Every sentence adds distinct value, 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?

Since there is no output schema, the description carries the responsibility of explaining what the response contains, and it does so thoroughly: store name, domain, currency, plan, email, timezone, product count, and locations. It also explains the no-input contract and the cost fields, so an agent has enough information to call and interpret the tool correctly.

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

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

The tool has zero parameters and the schema already communicates that perfectly. The description reinforces this with 'Аргументов не принимает' and explains why no shop argument is needed, which is useful context for an agent that might otherwise look for a shop selector 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 description uses a specific verb ('Возвращает') and names a concrete resource: the shop bound to the server, including its domain, currency, plan, and locations. This clearly distinguishes get_shop from sibling tools like get_product and list_orders, and the no-argument behavior is stated explicitly.

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 explains that the tool takes no arguments and that the shop is determined by SHOPIFY_STORE_DOMAIN, so an agent knows when it can call this tool. It also connects the returned location IDs to set_inventory, giving a concrete downstream use case. It does not explicitly discuss alternatives or exclusions, but none are really needed for 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?

The description goes far beyond the annotations. It explains why destructiveHint is set (documents may be mutations), warns that HTTP 200 does not mean success for mutations (userErrors must be checked), discloses that mutations are not retried to avoid double application, that THROTTLED is auto-retried, and that the cost is returned in the response with a 1000-point limit. These are critical behaviors not visible in 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 description is dense but each sentence earns its place. It front-loads the core purpose and usage, then flows logically through the destructive annotation, userErrors caveat, retry semantics, and cost limits. No redundant or vague content.

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

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

For a complex, open-world GraphQL tool with no output schema, the description provides all essential context: purpose, auth (token/shop/API version inserted by server), error interpretation (userErrors), retries, and cost. An agent has enough to call it correctly and know what to inspect in the response.

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 schema already documents all three parameters. The description restates that variables are passed via 'variables' and implies queries are safe, but adds no substantive meaning beyond the schema's property descriptions. 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 action (executes an arbitrary GraphQL document against the Admin API) and explicitly clarifies it's the catch-all for operations lacking a dedicated tool, listing examples. This distinguishes it from the sibling tools (e.g., get_product, create_product) 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 says to use this tool for everything that does not have a separate tool, providing examples like metafields, media, collections. This is a clear when-to-use instruction and implies using dedicated siblings when they exist. It also adds operational cautions about mutation vs query and retry behavior.

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

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

Annotations already provide readOnlyHint and destructiveHint, but the description goes well beyond them: it guarantees no creation or mutation, names graphql_request as the only mutation path for personal data, discloses the required OAuth scope, and explains the cursor-based pagination contract (hasNextPage/endCursor → after). This is exactly the kind of behavioral context an agent needs.

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, each earning its place: return shape, pagination protocol, and safety/scope. The most important information is front-loaded and there is no filler or repetition of obvious facts.

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 paginated list tool with query-filter syntax and no output schema, the description covers all essentials: page contents, count semantics, cursor mechanics, query examples, side-effect guarantees, and required scope. An agent can invoke this tool correctly without needing to inspect the schema or sibling tools.

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 schema already documents all three parameters. The description still adds value by explaining the pagination round-trip (response endCursor becomes the next call's after) and by illustrating the query field syntax. This goes slightly beyond the static parameter descriptions, which warrants a 4 rather than a baseline 3.

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: 'Возвращает страницу клиентов' plus the exact fields returned (name, email, phone, order count, total spent, city). This clearly distinguishes it from get_customer (which fetches a single customer) and from list_products/list_orders. No ambiguity about what the tool does.

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 concrete usage context: cursor pagination flow, query string formats, and the read_customers scope requirement. It also explicitly states this tool does not create or modify customers and that modifications go through graphql_request. It does not explicitly say 'use get_customer for a single customer', but the list-vs-get distinction is strongly implied by the sibling names.

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, openWorldHint, idempotentHint, and destructiveHint false. The description adds behavioral detail beyond annotations by explaining pagination mechanics, exposing that code discounts include up to 5 codes and an application counter, and reiterating safety. No contradiction with annotations.

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

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

The description is compact and well-ordered: purpose, return fields, pagination, query syntax, and safety note. Every clause contributes meaningful information without redundancy or 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?

With no output schema, the description compensates by listing the returned fields and pagination contract. All three optional parameters are fully covered by the schema and reinforced by the description, making the definition complete 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 coverage is 100%, so the baseline is 3. The description adds value by illustrating real query strings and mapping endCursor to the 'after' parameter, which gives practical meaning beyond the schema definitions.

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+resource ('Возвращает страницу скидок магазина') and enumerates the returned fields, making the tool's purpose explicit. It also distinguishes itself from mutation siblings by stating it creates and disables nothing, which differentiates it from create_basic_discount.

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 provides concrete usage context: Shopify query syntax examples, cursor-based pagination instructions, and a clear read-only scope. It does not explicitly name an alternative or when-not-to-use case, but the context is unambiguous enough for correct selection.

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

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

Annotations already provide readOnlyHint=true and idempotentHint=true, but the description adds meaningful behavioral context: it includes inactive locations, and it spells out the attributes returned. The note about typical store size and default pagination is also useful behavioral information. No contradiction exists between description and annotations.

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

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

The description is exactly two sentences, front-loaded with the main purpose and fields, followed by the set_inventory wiring and pagination advice. Every sentence earns its place, with no filler or repetition.

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

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

For a simple read-only list tool with one optional parameter, no output schema, and annotations covering the safety profile, the description is complete. It tells the agent what the tool returns (including inactive items), which fields are present, how it relates to set_inventory, and that the default page size usually suffices. Nothing essential 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?

The schema already covers the 'first' parameter fully (integer, 1..250, default 20), so the baseline is 3. The description adds value by stating that the default page size is enough for most stores, providing practical guidance on parameter usage beyond the schema's formal constraints.

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

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

The description uses a specific verb 'Возвращает' with a clear resource 'локации магазина', and enumerates the returned fields (id, название, адрес, активность, выполняет ли онлайн-заказы). It also distinguishes itself by explaining that its id is needed by set_inventory, which clearly separates it from other list tools like list_products or list_orders.

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

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

The description gives an explicit use case: use this tool to obtain the location id for set_inventory. It also notes that most stores have only one or two locations, so the default page size is sufficient. However, it does not explicitly name alternatives or state when not to use this tool, so it falls just short of a 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?

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses meaningful behaviors: pagination returns hasNextPage/endCursor, a count under the same filter, and the critical caveat that orders older than 60 days are silently omitted without the read_all_orders scope. This is exactly the kind of contextual disclosure an agent needs.

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?

Every sentence in the description earns its place: the first states what is returned, the second explains pagination, the third gives query examples, and the fourth covers authorization. It is information-dense without being bloated.

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?

Despite lacking an output schema, the description tells the agent exactly what to expect: page fields, count, cursor fields, and edge cases like silent omission. It also covers the entire call flow from initial request to next-page continuation, making it complete for an agent to invoke 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?

The schema already covers all three parameters, and the description adds extra value by explaining that 'after' accepts the endCursor from the previous page and giving rich query string examples for the 'query' parameter. This goes beyond simple schema descriptions, though the coverage means the baseline is already solid.

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 explicitly states the tool returns a page of orders, newest first, with a defined list of fields (number, date, financial status, fulfillment status, amount, client) and a count under the same filter. This clearly distinguishes it from sibling tools like get_order or cancel_order, even without naming them.

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

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

The description provides detailed usage instructions: cursor pagination flow, query syntax with concrete examples, and required OAuth scopes. It does not explicitly say 'use this instead of get_order for listings', so it lacks direct alternative routing, but the context is unambiguous enough for a listing tool.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description is fully consistent with them — no contradiction. Beyond annotations it adds real behavioral value: the response shape (count under the same filter, pageInfo hasNextPage/endCursor), the cursor-continuation dependency across calls, and cost-bucket optimization behavior. The 'Shopify has no page number' note preempts a common misuse.

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 earning its place: return shape, pagination mechanics, query syntax, cost guidance. The primary function is front-loaded in the first sentence, and the field enumeration is justified because no output schema exists to carry that information. No filler, no repetition of the title, logically ordered from what → how to paginate → how to filter → how to size.

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

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

With no output schema, the description correctly compensates by enumerating return fields, count, and pageInfo. Pagination, query filtering, and page sizing are all fully specified, and the annotations carry the safety profile (read-only, idempotent, non-destructive). The only gap is error behavior on invalid queries, which is minor for a read-only list tool.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema: for 'after' it explains the full pagination loop (response endCursor feeds the next call), and for 'first' it adds cost-bucket sizing guidance absent from the schema. The 'query' examples largely mirror the schema, contributing less incremental value.

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: 'Возвращает страницу товаров магазина' with an explicit return-field list (id, name, handle, status, vendor, type, tags, total inventory, up to 5 variants with prices) plus count. The page/filter framing distinguishes it from get_product (single resource) and the create/update mutations among siblings. No tautology — the description adds field-level and behavioral detail far beyond the title.

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?

Provides clear operational context: cursor pagination flow (endCursor from pageInfo → pass to after), the explicit warning that Shopify has no page-number parameter, query string examples ('status:active', 'vendor:Nike created_at:>=2026-01-01'), and page-size guidance (up to 250 per call is cheaper by cost bucket). It does not explicitly route to alternatives like get_product for single-item lookups, so it stops short of a 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?

Beyond the annotations (idempotentHint, readOnlyHint=false), the description discloses that repeated calls with the same numbers are no-ops, that reservations are untouched, that movement history is not written, and that failures surface as userErrors. This is exactly the kind of behavioral context that helps an agent predict side effects. No contradiction with annotations.

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

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

Three dense, purposeful sentences. The most important semantic distinction (absolute set, not delta) is first, followed by parameter provenance, then behavioral side effects and failure mode. There is zero redundancy or filler.

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

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

For a two-parameter mutation with no output schema, the description covers the operation's core semantics, required parameter sources, default values, side effects, and error behavior. The failure examples (untracked items, unlinked locations) are particularly useful for an agent to diagnose errors. Nothing essential 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?

Although the schema already documents all parameters (100% coverage), the description adds critical semantic clarification: inventoryItemId is the inventoryItem variant id from get_product and explicitly NOT the variant id, locationId comes from list_locations, and reason defaults to correction. This prevents a highly likely misuse of the wrong 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 states a specific verb and resource: 'Устанавливает АБСОЛЮТНЫЙ доступный остаток позиций на локациях' and explicitly contrasts with incremental changes ('не «изменить на N»'), making it unambiguous and distinct from sibling mutation tools like update_variant. The key nuance of absolute vs delta is front and center.

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 clear operational context: it tells the agent how to source inventoryItemId from get_product and locationId from list_locations, and states the default reason. It also provides implicit exclusions ('Историю движений не пишет и резервы не трогает'), but it does not explicitly name an alternative tool for cases like incremental adjustments or history-writing operations.

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

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

The description goes well beyond annotations by disclosing partial-field overwrite semantics, full replacement of tags, the storefront effect of DRAFT, reversibility of ARCHIVED, and that failures surface as userErrors. This gives the agent a detailed operational model without requiring extra inference.

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 compact and information-dense: core overwrite behavior first, then tag replacement, exclusions, alternative tools, and status edge cases. Every sentence adds value and there is no repetition or filler.

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

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

For a 7-parameter update tool with no output schema, the description covers what matters for correct invocation: affected fields, nontrivial tag/status behavior, adjacent tool routing, and error handling. Nothing essential is missing.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds meaningful extra semantics by clarifying that tags replace the entire list and by giving real-world consequences for status values, which the schema does not fully communicate.

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 clear verb and resource: 'Перезаписывает переданные поля товара' and explicitly lists the affected fields. It also distinguishes itself from update_variant and set_inventory by stating that prices and stock are not changed 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?

The description explicitly states this tool is for updating product metadata fields and that prices and inventory belong to other tools, naming update_variant and set_inventory as alternatives. It also explains the operational meaning of status values, so an agent knows exactly when and how to use it.

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

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

Annotations already declare readOnlyHint=false/not read-only, destructiveHint=false, and idempotentHint=true. The description adds important context: only price and compareAtPrice are affected, compareAtPrice:null removes the strike-through price, failures arrive as userErrors, and the call is limited to one product. It does not repeat annotation data, and no contradiction 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?

Every sentence carries distinct information: main function, scope limit, value format, null semantics, exclusions, prerequisite, and error behavior. It is dense but well-structured and does not restate the title 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?

The description covers all necessary context for a simple two-parameter write tool: required parent id, variant id format, value format, null handling, limits, and error reporting. With no output schema and 100% schema coverage, nothing essential is missing.

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

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

Schema coverage is 100%, so the schema documents both parameters. The description adds semantic value beyond the schema: amounts are decimal strings in shop currency, compareAtPrice:null clears the old price, and only price fields are changed—not other variant attributes.

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

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

The description uses a specific verb ('Задаёт') with a clear resource: prices and compareAtPrice for variants of one product. It explicitly states what it does NOT change (SKU, barcode, options), which distinguishes it from sibling tools like update_product and graphql_request.

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 when to use this tool (set price/compareAtPrice on variants) and when not to (other variant fields via graphql_request). It also specifies the prerequisite: parent product id from list_products/get_product.

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