Nature's Wild Berry

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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so safety is fully covered. The description's 'Read-only' simply restates that, and 'Approved facts' adds only a small note about content curation, with no mention of freshness or source of truth.

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?

One substantive sentence, front-loaded with the content scope and no padding. The trailing 'Read-only' is redundant with the annotations and slightly erodes the economy.

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 parameterless static-facts tool with no output schema, the description covers the breadth of returned content adequately. It could note the response form (single fact sheet versus grouped sections), but nothing essential for calling it correctly is missing.

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

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

Zero parameters, so the schema carries nothing to explain; this is the baseline case where the description need not discuss inputs.

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?

Names the specific resource and enumerates its scope: the berry, its three taste effects, the company and its certifications. An agent can distinguish it from get_products or get_policies, though the retrieval verb itself is only implied.

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

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

Gives a content scope that hints at usage but never states when to choose this over ask_nwb, how_to_use, or where_to_buy. No prerequisites, exclusions, or alternatives are named.

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, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral detail beyond the annotations: it returns the answer word for word and provides the exact fallback message when no approved answer exists. It does repeat the read-only nature, but the fallback disclosure is valuable.

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 three short sentences and front-loads the primary action. It is appropriately sized for a simple lookup tool, though the final 'Read-only' sentence is redundant given the annotations.

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

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

For a one-parameter read-only lookup with no output schema, the description covers the key behavior: what it returns, how it returns it, and what happens when no approved answer exists. It does not explain the source or scope of approved answers, but that is a minor gap for this simple 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 description coverage is 100%, so the single 'question' parameter is already documented in the schema. The description adds little parameter-level meaning beyond saying the lookup is by topic, which slightly mismatches the schema's wording of 'question'. Baseline 3 is appropriate when the schema carries the parameter semantics.

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: looks up an approved answer by topic and returns it word for word. It is clear what the tool does, but it does not explicitly distinguish itself from sibling information tools such as about_nwb, get_policies, or how_to_use.

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 its siblings. The description implies a question-answering use case, but it does not state when-not to use it or name any alternative 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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description still adds genuinely useful behavior: nothing is bought until checkout, and the Shopify agent checkout endpoint does not support subscriptions, which is a real limitation an agent would otherwise miss. It stops short of detailing link expiration or multi-item failure behavior.

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?

One dense but front-loaded sentence with the return value stated first, followed by the checkout caveat. 'Read-only.' is a minor redundancy with the readOnlyHint annotation, but the rest 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?

With no output schema, the description carries the return-value burden and does so: it enumerates the link, the line-by-line summary, and the checkout endpoint. Combined with full schema coverage and annotations, an agent has everything needed to invoke and interpret this 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, but the description maps the subscribe boolean to 'one-time or Subscribe and Save' and clarifies that variants correspond to the items added, which is more than the schema alone conveys. It is not fully redundant with the schema.

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

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

States a specific verb (build) and resource (cart link), plus what the returned link does: fills the shopper's cart with chosen variants, one-time or Subscribe and Save. This clearly separates it from read-only siblings like get_products and get_policies, so an agent knows this is the cart-construction tool.

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 ties the tool to get_products by specifying that variant_id comes from that sibling, which is the key routing context. It stops short of an explicit when-not or an alternative, but the context is clear enough to invoke correctly.

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 'Read-only' in the description merely repeats structured data and earns no credit. The description does add a return-format hint that results include links to policy pages, which is useful context, but it says nothing about freshness, caching, or failure modes.

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 with no filler; what the tool returns is front-loaded, and the read-only note is brief. Nothing could be cut 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-argument, read-only retrieval tool with no output schema and full annotation coverage, the description tells the agent what content to expect and that links are included. It could add a note on when content might be missing or stale, but it is sufficient to call 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 input schema has zero parameters, so the baseline is 4. Nothing in the description misrepresents or omits parameter behavior since there is nothing to parameterize.

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 (approved shipping and guarantee summaries, store policy pages) with a clear scope, letting an agent distinguish it from siblings like about_nwb or how_to_use. It is not a tautology of the name, though it lacks an explicit verb such as 'retrieve'.

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 purpose implies when the tool is relevant (questions about shipping or guarantees), but there is no explicit when-to-use or when-not-to-use guidance and no mention of alternatives. For a zero-parameter, single-purpose lookup tool the intent is largely self-evident, so this is adequate rather than strong.

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 the safety profile is covered. The description adds useful context about review screening ('reviews that passed review screening') which isn't in the annotations. However, it doesn't disclose rate limits, authentication requirements, or pagination behavior, so with annotations raising the bar, this is adequate but not rich.

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

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

The description is a single dense sentence front-loading the returned fields, followed by a terse 'Read-only' confirmation. It is efficient, though the long list of fields makes it slightly less scannable.

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 one optional parameter and no output schema, the description covers return fields well. But it omits usage guidance and any behavioral details beyond the safety hint, leaving minor completeness gaps for an agent deciding when to invoke it.

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

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

Schema description coverage is 100%, so the single 'query' parameter is fully documented in the schema. The description doesn't add syntax, format, or examples beyond what the schema provides, making 3 the baseline.

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 (get) and resource (products) and enumerates exactly what is returned: names, prices, crossed-out prices, variant_id, Subscribe and Save availability, product and checkout links, and screened reviews. This clearly distinguishes it from siblings like build_cart 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?

No explicit when-to-use guidance is provided. The description lists returned fields but doesn't say when to call get_products versus ask_nwb, where_to_buy, or build_cart, nor does it mention prerequisites or exclusions.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so 'Read-only' merely restates structured data. The description adds no behavioral context such as whether the steps are fixed/canonical, whether the effect duration varies by person, or how the content 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?

It is short with no padding, which is good, but it is telegraphic to the point of being a fragment rather than a sentence, and 'Read-only' is wasted words given the annotations. It reads like a content summary rather than a tool description.

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

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

For a zero-parameter, read-only lookup with no output schema, the definition is adequate but thin: it doesn't say what form the answer takes (steps list? prose?), nor how it differs from the adjacent about_nwb/ask_nwb tools. Complete enough to invoke, not complete enough to choose confidently.

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 there is nothing for the description to disambiguate; the baseline for a no-param tool applies. No parameter confusion is possible.

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 conveys the content domain (the four approved steps, serving guidance, effect duration), so an agent can guess this returns usage instructions. But it has no verb and never says plainly 'returns how-to-use instructions,' and it doesn't distinguish itself from siblings like about_nwb or ask_nwb that plausibly cover similar ground.

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 at all, and no routing relative to siblings such as about_nwb (background info) or ask_nwb (free-form Q&A). The agent must infer that this is the canonical usage-steps source.

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 a closed-world scope, so the safety profile is fully covered without the description. The description's 'Read-only' merely restates readOnlyHint, adding no new behavioral context such as rate limits or freshness of the link list.

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 that leads with what the tool returns. The trailing 'Read-only' is wasted since annotations already carry that flag.

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 must convey the return shape, and it does (marketplace entries plus links, and the company's own store). It could say more about ordering or whether marketplaces are region-specific, but 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?

Zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description appropriately uses its space to describe the return content instead.

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 (consumer marketplaces selling Nature's Wild Berry, plus the company's own store) and states the payload shape (each with its link). It is clearly distinguishable from get_products and wholesale_and_foodservice by audience, though it never explicitly contrasts 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?

No when-to-use guidance, no prerequisites, and no alternatives named. An agent must infer that this is the purchase-channel lookup rather than, say, the product catalog.

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, destructiveHint=false and a closed world, so safety is well covered. The description's 'Read-only' simply restates the annotation, adding no new behavioral detail; the 'No wholesale prices' scope note is the only genuinely additive information.

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

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

Three short sentences, front-loaded with the topic and followed by the two constraints. Nothing is padded, though the trailing 'Read-only' is redundant with the annotations.

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

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

With no parameters, no nested objects and no output schema, the definition has little to explain, and the annotations carry the safety profile. Still, it never says what the tool actually returns (guidance text? contact list? ordering process?), leaving the agent to guess at the output shape.

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 there is nothing for the description to disambiguate. Baseline 4 applies; no parameter meaning is missing.

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 concrete resource (the Travel Case) and audience (stores/foodservice operators), so the topic is identifiable. However, the verb is oblique – 'How ... can order' is a content/FAQ framing, not a stated action, and it doesn't distinguish itself from the sibling 'where_to_buy', which plausibly covers the same ordering question.

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 wholesale prices' implies a when-not constraint (don't use this for pricing), which is a small usage signal. But there is no statement of when this tool should be selected over 'where_to_buy' or 'get_policies', and no preconditions or alternatives are offered.

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