Nature's Wild Berry

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false and destructiveHint=false, so 'Read-only' in the description is redundant with structured data. The one genuine addition is 'Approved facts', which signals curated, authoritative, static content rather than generated answers — a useful contrast with ask_nwb.

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 listing the content, with no padding. The trailing 'Read-only.' fragment restates the annotations rather than earning its place, which keeps it short of 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?

For a zero-parameter, fully annotated read tool the description is nearly sufficient — an agent knows what it returns and that it is safe to call. What is missing is the boundary against ask_nwb, the closest sibling, which is the one piece of context that would prevent a mis-selection.

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 takes zero parameters and the schema is empty, so there is nothing for the description to disambiguate. Baseline 4 applies for a no-parameter tool.

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 resource and enumerates its content ('facts about the miracle berry, its three taste effects, the company and its certifications'), which tells the agent exactly what it will get back. It does not, however, distinguish itself from the sibling ask_nwb, which is the tool most likely to be confused with it for informational queries.

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 and no mention of alternatives. With a sibling named ask_nwb that appears to answer questions about the same subject matter, the absence of any routing rule ('use this for the fixed facts; use ask_nwb for open questions') leaves the agent to guess.

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 safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the trailing 'Read-only' adds nothing. The description does add genuinely useful behavior beyond the annotations: the answer is returned word for word, and on no match a fixed message with a contact email is returned — this pre-empts an agent misreading the fallback string as a real answer.

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, no filler, and the core behavior plus the fallback case are front-loaded. Every sentence carries information an agent needs to interpret the response correctly.

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, no-output-schema tool whose annotations already declare safety, the description covers the main behavior and the miss case, which is what an agent needs. The one remaining gap is how 'approved answer' matching is decided (exact topic vs. fuzzy), which would matter for phrasing the question.

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

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

Schema description coverage is 100% for the single 'question' parameter, so the schema already carries the semantics and baseline 3 applies. The description's phrase 'by topic' adds a hint about how matching works (topic lookup rather than free-form Q&A), but it never clarifies the relationship between 'topic' and the 'question' 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 — looks up an approved answer by topic and returns it verbatim — which an agent can distinguish from write tools like build_cart. It does not, however, differentiate itself from overlapping informational siblings such as about_nwb, how_to_use, or get_policies.

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 use this tool versus the informational siblings (about_nwb, get_policies, how_to_use), nor any prerequisite or exclusion. The only implicit guidance is the fallback behavior, which tells the agent what happens on a miss rather than when to reach for this tool at all.

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

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

Annotations already declare readOnly, idempotent, non-destructive, open-world. The description adds genuine context beyond that: 'Nothing is bought until the shopper checks out', the return includes a line-by-line summary and a Shopify agent checkout endpoint, and that endpoint excludes subscriptions. Slight redundancy restating 'Read-only' costs a little.

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?

Effectively a single dense sentence, front-loaded with what is returned (the link) before the caveats. It earns its length, though the trailing 'Read-only.' is redundant with the 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?

No output schema exists, so the description carries the return-value burden and does so by naming the link, a line-by-line summary, and the checkout endpoint. It covers the essential behavioral caveats; only a stronger when-to-use cue 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 already documents items, quantity (1-10), subscribe, and variant_id. The description echoes the one-time vs Subscribe-and-Save distinction but adds no format or constraint detail beyond the schema. 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?

Specific verb+resource: returns a natureswildberry.com cart-fill link for chosen variants. It clearly distinguishes itself from siblings like get_products and recommend_product by describing its unique output (a cart link plus checkout endpoint).

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 the tool is used after selecting variants (one-time or Subscribe and Save), and notes the checkout endpoint does not support subscriptions. But it never explicitly states when to reach for this tool versus siblings like get_products (which supplies variant_id). Usage is inferable rather than 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, idempotentHint=true, and destructiveHint=false, so 'Read-only' largely restates structured data. The description does add useful content-level context ('approved' summaries with links to policy pages), but says nothing about return shape, caching, or whether links are absolute.

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, front-loaded with the resource scope. The trailing 'Read-only' sentence is redundant against readOnlyHint in annotations, which costs it a point.

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-parameter, no-output-schema read tool, the description conveys what comes back (summaries plus links to policy pages), which is the key missing piece an agent would otherwise lack. It is complete enough, though a hint about coverage (which policies exist) would help.

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?

Zero parameters, so there is no parameter semantics to clarify; baseline 4 applies. There is nothing the description could add or omit here.

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 resource (shipping and guarantee policy summaries) retrieved in a read-only manner, which is more concrete than the bare name get_policies. It does not explicitly contrast itself with near-neighbors like about_nwb or how_to_use, 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 only implied by the content type: an agent can infer this is the tool for policy questions, but there is no explicit when-to-use statement and no named alternative for adjacent information needs (about_nwb, how_to_use). Minimum viable 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, idempotentHint, openWorldHint and destructiveHint=false, so the trailing 'Read-only.' sentence earns no credit. The one genuinely additive behavioral detail is that returned reviews 'passed review screening,' which tells the agent the review data is pre-filtered/curated rather than raw.

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 dense sentence front-loads the returned payload, followed by a short redundant tag. The field list is efficient and information-dense, but 'Read-only.' duplicates the annotation block rather than earning 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?

With no output schema, the description carries the return-value burden and does so thoroughly, so an agent knows what a call yields. It is weaker on usage context and never explains the query filter's role, which keeps it short of complete for a discovery tool with several overlapping siblings.

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

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

Schema description coverage is 100% for the single 'query' parameter, so the schema already explains the filtering behavior and the maxLength constraint. The description adds nothing about the query parameter, which is acceptable at full coverage but not value-adding.

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 names a specific resource (products) and enumerates exactly what is returned: live names, prices, crossed-out prices, variant_id, Subscribe and Save availability, product link, checkout link, and screened reviews. That makes the tool identifiable, though the verb is implicit and it never contrasts itself with siblings like recommend_product or where_to_buy.

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, no prerequisites, and no alternatives named. With siblings such as recommend_product, where_to_buy and build_cart in scope, an agent gets no signal about which of them to pick for a product-data need versus a recommendation or purchase flow.

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 only behavioral claim, 'Read-only,' merely restates the readOnlyHint annotation, adding nothing. The phrase 'the approved four steps' hints at fixed canonical content, which is mildly informative, but nothing about freshness, scope, or limitations is disclosed.

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 very short fragments with no padding, and the content list is front-loaded. It is a sentence fragment rather than a well-formed statement, which slightly hurts readability.

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

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

With no output schema and no parameters, the description carries the burden of explaining what comes back; it partially does so by listing the content sections, but never frames this as a retrieval of usage guidance nor mentions the answer's format.

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 takes zero parameters, so the schema is trivially complete and there is nothing for the description to disambiguate. Baseline 4 applies for a 0-parameter tool.

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 names the content it returns (four steps, serving, effect duration) but never states a verb or explicitly says it retrieves usage instructions; that only comes from the tool name and title. It is distinguishable from siblings like where_to_buy or get_policies only by inference from the noun 'steps/serving/effect'.

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 call this versus alternatives such as about_nwb or ask_nwb, nor any stated prerequisites. The agent must guess that this is the canonical source for usage instructions.

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 safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely useful context beyond them: the return shape is a current price plus either a one-time cart link or a website subscription path, and in-chat checkout availability depends on the shopping platform. The closing 'Read-only' is redundant with readOnlyHint but not contradictory.

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 core matching function and followed by return/output behavior. Every sentence carries information except the trailing 'Read-only,' which duplicates an 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?

With no output schema, the description correctly carries the return-value burden (price, cart link, subscription path) and notes the platform dependency for in-chat checkout. It does not cover edge cases such as no-match behavior or whether the cart link expires, leaving minor gaps for a two-param tool.

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

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

Schema coverage is 100% with both enums documented, which sets a baseline of 3. The description earns above baseline by mapping values to behavior: 'first purchase, a group or a refill' echoes the need enum, and 'one-time cart link or the website subscription path' explains the consequence of each purchase 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?

Specific verb+resource: it 'matches' a shopper need to a 'live product' and states what comes back (price plus cart link or subscription path). That inherently separates it from catalog siblings like get_products and from cart-mutating siblings like build_cart, though no sibling is named explicitly, 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?

The opening sentence implies when it applies (a first purchase, a group, or a refill) and the purchase enum hints at routing, but there is no explicit when-to-use versus get_products/build_cart/where_to_buy, and no exclusion conditions. Usage is inferable rather than 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, idempotentHint, non-destructive, and closed-world, so the trailing 'Read-only' is redundant rather than additive. The description does add content scope (that results include links, physical-store status, ordering and pricing info), but says nothing about data freshness, auth, or limits beyond what annotations provide.

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

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

A single sentence is appropriately sized for a parameterless lookup tool and front-loads the core subject. The enumeration ('each with its link, plus our own store, whether we are in physical stores, how orders are placed and where prices are shown') is slightly run-on but every clause maps to a distinct piece of returned 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-param, no-output-schema lookup, the description usefully enumerates what the response covers, which compensates for the absent output schema. It is complete enough to call correctly; only the routing versus sibling tools remains unstated.

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 takes zero parameters, so the schema baseline of 4 applies. There is nothing for the description to disambiguate on the input side.

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 identifies the resource: consumer marketplaces plus the brand's own store, what to expect (links, physical-store presence, ordering, price display). It reads as a noun-phrase content list rather than a verb+resource statement, and it never names a sibling to distinguish itself from the near-colliding wholesale_and_foodservice tool, though 'Consumer marketplaces' implicitly contrasts with wholesale.

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 only implied by the name and content list; there is no explicit when-to-use, no when-not-to-use, and no alternative named. An agent can reasonably infer this is the lookup for retail purchase options, but nothing in the text routes it against get_products, wholesale_and_foodservice, or how_to_use.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'Read-only' is largely redundant. 'No wholesale prices' is the one piece of added behavioral content, scoping what the response will not contain, but nothing is said about the shape or limits of what is returned.

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 fragments, front-loaded with the subject matter. The trailing 'Read-only' duplicates the annotation rather than earning its place, but overall it is tight and readable.

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

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

For a zero-parameter, no-output-schema informational tool, the description conveys the topic adequately. It stops short of describing the form of the returned content, which is the only real 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?

The tool takes zero parameters, so the baseline is 4. There is nothing for the description to disambiguate on the input side.

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 concrete subject: how stores and foodservice operators order the Travel Case. It is clear what content the tool surfaces, though it does not explicitly contrast itself with near-neighbors like where_to_buy or about_nwb.

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 only routing hint is the negative 'No wholesale prices,' which tells the agent what it won't get but not when to pick this tool over where_to_buy or get_products. No positive trigger or alternative is named.

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