Limor Gilat herbal shop

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

The destructiveHint=true annotation already tells the agent this is a destructive mutation; the description adds nothing beyond that, such as whether cancellation is reversible, whether held inventory is released, or whether a cancelled checkout can be resumed. With annotations present the bar is lower, but the description restates the name rather than enriching it.

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

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

A single front-loaded sentence with zero waste, but its brevity reflects under-specification rather than disciplined editing. There is no structural signal, such as prerequisites or a note on what the call returns.

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?

This is a destructive mutation with two parameters, no output schema, and an undocumented required ID. The description provides none of the state, permission, or post-condition context an agent needs before invoking 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?

The 'id' parameter has no schema description, and the description never says what it identifies (presumably a checkout ID) or what format it takes. With only 50% schema coverage, the description needed to compensate and does not.

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 ('Cancel') and resource ('a checkout'), which is clearly distinguishable from siblings like complete_checkout or update_checkout. It stops short of specifying scope, such as whether it works only on pending checkouts or applies to any state.

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

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

No when-to-use, when-not-to-use, or alternative guidance is given. The most relevant sibling, complete_checkout, is an obvious fork in the road (cancel vs. finalize) that the description never addresses.

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?

With no annotations, the description carries the behavioral burden and usefully discloses that this tool does not complete the order but returns an escalated checkout with a payment URL. It does not state whether the checkout state is mutated, what permissions are required, or what errors may occur, leaving important behavioral gaps.

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

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

The description is a single, front-loaded sentence that immediately clarifies the counterintuitive behavior and then states the return values. Every clause earns its place.

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

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

The description covers the key non-obvious outcome (escalation URL instead of order completion) and partially compensates for the lack of an output schema. However, given the nested `checkout` parameter, low schema coverage, and absence of annotations, it leaves too much unexplained about invocation and side effects.

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 only 33%, and the description provides no information about the three parameters (`id`, `meta`, `checkout`). It does not clarify what `id` refers to, what the `checkout` object should contain, or how `meta` is used.

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

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

The description clearly states the tool's actual behavior: it returns the checkout with status `requires_escalation` and a `continue_url` for the buyer. It also explicitly clarifies that the store does not complete orders through the API, which prevents misinterpretation from the name `complete_checkout`. It does not explicitly contrast with sibling tools like `get_checkout` or `update_checkout`, so it falls 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?

Usage is implied: call this when completing a checkout requires escalation and the buyer must be redirected via `continue_url`. However, there is no explicit guidance on when to use this versus `get_checkout`, `update_checkout`, or other siblings, nor any stated preconditions.

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?

With no annotations, the description carries the full burden. It usefully discloses the non-payment nature and the redirect flow, plus the return contents, but says nothing about idempotency (repeat calls creating duplicate carts), required auth, or what happens to prices/stock at creation time.

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

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

Two tight sentences with no waste: the creation-and-return contract is front-loaded and the critical constraint (payment happens on the website) follows immediately.

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

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

No output schema exists, and the description compensates by naming what is returned (totals, delivery options, continue_url) and the required next step. Minor gap: nested buyer/discounts/context parameters are not addressed.

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 50%, and the description body adds no parameter-level meaning beyond restating the return contract; the item.id origin and fulfillment shape are documented in the schema itself, while buyer, discounts, meta, and context remain undocumented in both places.

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 priced checkout (cart)') and immediately names the return payload, which lets an agent distinguish it from get_checkout/update_checkout 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 clear context: the buyer must be sent to continue_url to review and pay, and the API never takes payment. It does not explicitly route to siblings (update_checkout for changes, get_checkout for retrieval, complete_checkout's role), so it falls short of full when/when-not 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?

The readOnlyHint annotation already covers the safety profile, so the description earns credit for what it adds: a concrete disclosure of the returned content domains (ownership, delivery, policies, ordering). With no output schema, this enumeration is the only signal of what an agent gets back.

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

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

A single front-loaded sentence with a colon-delimited content list and zero filler. Nothing could be removed without losing 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 no-required-parameter, read-only info tool with no output schema, listing the returned content areas is close to sufficient. Slightly more context on whether the data is merchant-static vs. request-scoped would close the remaining gap.

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

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

There is a single optional 'meta' parameter, fully documented in the schema (100% coverage), including its example shape and the note that it is optional here. The description adds nothing about it, which is acceptable given the schema does the work — 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?

The description enumerates precisely what the tool returns: store ownership, delivery options and prices, policies, and ordering mechanics. That clearly separates it from the product/catalog/checkout siblings. It lacks an explicit verb ('get returns...'), but the resource 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?

There is no statement of when to call this versus alternatives such as lookup_catalog or get_product, and no prerequisites or exclusions. The only hint is the mention of 'how ordering works', which implies pre-checkout context but is not framed as 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?

The readOnlyHint annotation already declares this is a safe read operation, and the description is consistent with that. However, the description adds no behavioral context beyond the annotation—no mention of error behavior for missing checkouts, authentication needs, or what a checkout object represents.

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 a single front-loaded sentence with no wasted words. Its brevity is efficient, though the same terseness contributes to gaps in behavioral and usage guidance.

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

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

For a simple read-by-id tool with a readOnlyHint and a partially documented schema, the description is minimally adequate. However, with no output schema and no description of the returned checkout structure or common failure modes, it leaves meaningful context gaps for an agent.

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 only 50%: the 'id' parameter lacks a schema description while 'meta' is documented. The phrase 'by id' partially compensates by clarifying that the id identifies a checkout, but it gives no format or validation details for that required 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 states a specific verb and resource: 'Get a checkout by id.' This clearly distinguishes retrieval from sibling mutations like create_checkout, update_checkout, cancel_checkout, and complete_checkout. It does not explicitly name or differentiate against those siblings, but the verb/resource pairing 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?

There is no guidance on when to use this tool versus alternatives such as lookup_catalog or search_catalog, nor any exclusions or prerequisites. The only usage signal is the implied retrieval-by-id operation.

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

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds value by listing the returned fields, but says nothing about not-found behavior, whether the language preference affects the returned text, or completeness of pricing data.

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

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

A single front-loaded sentence with no wasted words, and the returned fields are listed immediately. It is arguably too thin rather than padded, so there is no structure problem.

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 read-only tool with no output schema and a nested `catalog.context` object, the description gives only a partial picture of the response and nothing about the optional context parameters. With annotations carrying the safety profile, this is borderline adequate but leaves real gaps.

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 only 33%: `id` and `catalog.context.intent` are undocumented, and the description mentions neither. It implies a single-product lookup but adds no meaning about the id format or how the optional catalog context changes results, so it 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?

The description states a specific retrieval action for a single product and enumerates the payload it returns (description, uses, variants, prices). That is clear enough to separate it from search_catalog and lookup_catalog, though it doesn't explicitly frame the lookup-by-id nature or name the siblings it differs from.

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 guidance on when to pick this over lookup_catalog or search_catalog, and no mention of what happens when the id is unknown. The agent is left to infer usage from the name alone.

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 readOnlyHint annotation already establishes that this is a safe read operation. The description adds little behavioral context beyond the id format: it does not mention batch lookup behavior, missing-id handling, or response characteristics. With annotations covering the safety profile, the remaining gaps are notable.

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

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

The description is a single efficient sentence with the key lookup criteria and id format front-loaded. No words are 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?

The tool has nested parameters and no output schema, but the description does not explain return shape, whether multiple ids are resolved in one call, or how missing ids are handled. For a lookup tool with this schema complexity, more context is needed.

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

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

Schema description coverage is 50%, and the description adds meaningful semantics for the ids parameter by explaining the slug and slug@ml formats. However, it does not clarify the required catalog wrapper or provide further detail on nested fields such as context and intent.

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 and resource: look up products or variants by id. It also clarifies the id format (product slug or slug@ml). It does not explicitly distinguish itself from siblings like get_product or search_catalog, but the 'by id' scope makes its role reasonably clear.

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 explicit guidance on when to use this tool versus search_catalog or get_product. The id-based lookup implies usage when identifiers are known, but no alternatives or exclusions 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?

With readOnlyHint=true already declaring safety, the description adds genuinely new behavioral context: matching covers both names and descriptions, both English and Hebrew are matched, and an empty query returns the full list. It does not disclose pagination/cursor behavior or result ordering, which would matter for a listing tool.

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, each earning its place: purpose first, matching/language semantics second, currency units third. Nothing is repeated from the schema and nothing is padding.

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

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

No output schema exists, and the description never characterizes the return shape or how pagination cursors work, which an agent needs for a listing tool with nested filters and pagination. The nested-object complexity is only partially addressed.

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?

At 50% schema coverage, the description compensates for the most consequential gap: prices are integer agorot (ILS minor units), which the bare integer min/max schema does not say. It also clarifies query matching semantics. However, filters.categories, pagination.limit/cursor, and the intent field are left entirely to the schema, so coverage is only partial.

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 ('Search the shop's herbal remedies and natural cosmetics'), which scopes the catalog to a concrete domain. It does not, however, distinguish itself from the sibling lookup_catalog or get_product, so an agent cannot tell from this text alone which of the two catalog tools to pick.

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?

'An empty query lists everything' implies a browse mode and hints at when to use it with no terms. There is no explicit guidance on when to prefer this over lookup_catalog, get_product, or when to apply filters, so selection between siblings remains 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?

With no annotations at all, the description carries the burden well by disclosing the key non-obvious semantic: line_items is replaced while omitted fields are preserved (PATCH-like), and 'Options are listed in the returned checkout' implies a checkout object is returned after mutation. It omits error behavior (invalid coupon code), inventory/price re-validation, and permission requirements, which keeps it below 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?

Two sentences, no filler, and the mutation scope is front-loaded before the merge-semantics caveat. Every clause conveys 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?

For a nested mutation tool with zero annotations and no output schema, the description answers what can be changed but not the full picture: no statement of the return payload shape, no failure modes for expired checkouts or invalid coupon codes, no indication of the required 'id' source. Adequate to start, but an agent would still guess on error handling.

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 low (33%), but the prose compensates by naming the exact nested paths for coupon codes (discounts.codes), the fulfillment selection shape, and what line_items.item.id means (a variant id from search_catalog). It says nothing about the top-level 'id' parameter (where to obtain the checkout id) or the 'meta'/'context' fields, leaving a residual 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 ('Change a checkout') plus the concrete mutable aspects: line_items, buyer, discount codes, delivery option. This unambiguously separates it from create_checkout, get_checkout, complete_checkout and cancel_checkout, which an agent can infer 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?

Usage is implied by the enumeration of what can be changed, and 'Fields you omit stay as they are' signals it is for incremental modification of an existing checkout. However, it never states prerequisites (an existing checkout id, likely from get_checkout) nor when to prefer create_checkout or complete_checkout instead.

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