Good Nature Vibe Catalog

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description usefully adds that results come from a public catalog feed and that checkout pricing is out of scope, but says nothing about result volume, pagination, or how the store view changes results.

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 English sentence is front-loaded and efficient, and the scope constraint lands early. The Dutch sentence is a near-verbatim restatement that adds length without new information for most agents, and the stray facet list ('category, brand') is noise.

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-required-parameter, fully documented read-only search tool with annotations, this is close to adequate. The remaining gaps are the phantom category/brand facets and the absence of any pointer to the sibling tool that supplies pricing or full product records.

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

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

Schema coverage is 100%, so the baseline would be 3, but the description actively introduces 'category' and 'brand' as search dimensions that are not parameters, which can mislead an agent into attempting unsupported filters. The 'short text' phrasing also loosely maps onto the query parameter without adding real 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?

States a specific verb+resource: 'Search or list products from the public catalog feed', and clarifies the discovery scope versus checkout pricing. However, it lists 'category, brand' as search facets that do not exist in the schema, and it never distinguishes itself from the sibling gnv_product tool, so an agent cannot fully disambiguate from the text alone.

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?

'Discovery only, not the checkout price' gives a clear boundary on what the tool is not for, and the schema notes leaving query out lists everything. But there is no explicit guidance naming gnv_product for full product details/pricing or gnv_knowledge_search for other lookups, so the when-to-use-this-vs-sibling decision is only implied.

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 and closed-world, so the safety profile is fully covered and the only added signal is "public" (implying no auth). With no output schema, the description carries the burden of saying what comes back, and it says nothing — one cannot tell whether the result is a string, a link, or a structured contact block.

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?

Very short and front-loaded, but roughly half the text is a Dutch restatement of the same sentence, which adds no decision-relevant information for an agent. The saved space could have carried a return-value hint.

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 lookup with no output schema, the description should at least characterize the returned content (contact details vs. a page link). It leaves that entirely unspecified, so an agent cannot judge whether calling it satisfies a contact-information need.

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 partial or misleading parameter claims are made.

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?

"Public contact path of the shop" names a resource (shop contact) and a qualifier (public), which distinguishes it reasonably from the catalog/product/knowledge siblings. However, "contact path" is ambiguous about what the tool actually returns — a URL, an address, phone/email fields, a web form? The verb is missing entirely.

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 guidance on when to invoke this versus the other shop tools, and no prerequisites or exclusions stated. An agent must infer that contact requests belong here purely from the word "contact".

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 scope, so the safety profile is fully covered. The description adds one genuinely useful behavior: it returns the complete plain text rather than an excerpt, and no filtering/user scoping applies. It says nothing about missing-id behavior or whether markup is stripped.

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 English sentence is front-loaded and tight, but the Dutch sentence is a verbatim translation that adds no information for an agent already reading the English text. Roughly half the description is redundant repetition rather than earned 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?

This is a simple two-parameter read tool with full annotation coverage and no output schema, and the description does state the return shape ('full plain text'). What remains unspecified — error behavior for an unknown id, and whether text includes markup — is minor for a tool this straightforward.

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

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

Schema coverage is 100% and both parameters already document the numeric id and the default store view code 'nl'. The description adds no syntax, format, or defaulting detail beyond what the schema provides, so the baseline 3 applies.

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

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

"Full plain text of one CMS page or blog post" names a specific retrieval verb and resource, and the word "one" plus "full plain text" separates it from the sibling gnv_knowledge_search, which returns matches rather than full content. It stops short of naming that sibling explicitly, so an agent must infer the pairing.

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 statement, no prerequisite about needing an id from a prior search, and no exclusion of alternatives. The only routing hint ("id ... from gnv_knowledge_search") lives in the schema, not the description, so the description itself gives no guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true and non-destructive, so safety is covered structurally. The description adds genuinely non-obvious behavior: empty-query default, a 100-item cap, and an explicit prompt-injection warning that retrieved text is data rather than instructions. It does not describe result ordering or truncation behavior beyond the cap.

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 English portion is front-loaded and waste-free, but the full Dutch translation repeats the entire content verbatim, roughly doubling the length without adding information for most agents. The result is still short, but the duplication is the largest inefficiency in the definition.

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 three-parameter, all-optional read tool with no output schema, the definition covers search-vs-list behavior and the result cap, which is what an agent needs to call it correctly. The main remaining gap is the absence of guidance on which sibling tool to prefer for adjacent content types.

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

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

Schema description coverage is 100%, so all three parameters (type, query, store) are already documented with defaults and semantics. The description only restates the empty-query behavior that the 'query' schema field already states, adding no new meaning such as matching rules or whether 'store' affects the result set.

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 verb ('Search or list') and resource ('CMS pages and blog posts'), which is clearer than the title alone. It does not explicitly distinguish itself from the sibling 'gnv_knowledge' or 'gnv_catalog_search', so an agent must still infer the boundary between knowledge content and catalog content.

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?

'Without a query the list is returned, at most 100' gives a usable rule for choosing list-mode versus search-mode. However, no alternative tool is named and there is no statement about when NOT to use this tool versus gnv_knowledge or gnv_catalog_search, leaving sibling routing to inference.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's main added value is disclosing the response contents: variants, price range, public text. That is genuinely useful since no output schema exists, but it omits behavior on failure (unknown SKU) and whether all variants are returned or truncated.

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

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

The core sentence is short and front-loaded, but roughly half the text is a Dutch translation that restates the same content verbatim for an English-reading agent, so not every sentence 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?

For a simple two-parameter read tool with full schema coverage, what to pass and what comes back are both covered. Missing are the edge cases an agent would want: behavior when the SKU is unknown, and whether the price range implies currency/store-view dependence.

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%, with sku and store both documented including the nl default, so the schema does the heavy lifting. The description adds no parameter-level meaning such as whether store affects price or variant availability, which is the baseline 3 case.

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 resource ('one product from the feed') and enumerates what comes back: variants, a price range, and the public product text. That is specific enough to distinguish it from gnv_catalog_search (a search over many products), though it never explicitly contrasts the two.

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 or when-not-to-use guidance in the description, and no alternative is named. The only routing hint ('Product SKU from gnv_catalog_search') lives in the schema, not the description, so an agent reading the prose alone gets no guidance about how to obtain a SKU or when to prefer the search sibling.

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 closed-world behavior, so the safety profile is covered. The description adds nothing beyond that — it does not say what the profile contains, whether it is static configuration or live data, or what the caller receives, and the Dutch restatement carries no behavioral information. It does not contradict 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?

It is very short and front-loaded, but the second sentence duplicates the first verbatim in another language, which adds length without adding information for most agents. Acceptable if the bilingual pattern is intentional across the server, otherwise waste.

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, no parameters, and no behavioral detail, the description leaves the agent unable to predict what this returns — field names, scope, or whether it includes settings versus descriptive copy. For a no-argument resource fetch this is the main gap and the description does not close 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 tool takes no parameters, so the baseline is 4 and there is nothing for the description to disambiguate. Schema coverage is nominally 100% with an empty property set.

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 is essentially a noun phrase that restates the title 'Merchant profile' with the brand name appended, and the second sentence is the identical statement in Dutch. It does implicitly separate this resource from siblings like gnv_product and gnv_contact, but there is no verb and no statement of what retrieving the profile actually gives you.

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 gnv_contact, gnv_product, or gnv_knowledge, and no prerequisites or exclusions are mentioned. An agent must infer that this returns general merchant-level information rather than contact or product data.

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