Habsziget Webshop

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds a real usage constraint (all three dimensions must exist), but never says what is returned — a price value, currency, or per-unit vs. total — which matters for a calculation tool with no output schema.

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

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

Four short sentences, front-loaded with purpose then the gating condition. Minor redundancy: the decimal-point/unit instruction duplicates what the schema already states three times.

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 computation tool with no output schema, the agent still needs to know what the result looks like (number? formatted price? includes quantity?). The precondition is covered but the return contract is not, leaving a meaningful 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?

Schema coverage is 100%, so every parameter is already documented, including unit and decimal-point guidance. The description's repetition of 'no cm unit, use a decimal point' adds no meaning beyond the schema and never mentions the optional quantity 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: it calculates the price of a custom cuboid/block or array. That distinguishes it implicitly from the generic get_product_price sibling, but the description never names that sibling or 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?

Gives an explicit precondition: only call when the customer has supplied all three required dimensions. It lacks a clear pointer to an alternative (e.g., get_product_price for standard products), so the use-vs-alternative routing is left implicit.

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, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds only the returned field set, with no note on freshness of the bank data or whether the details are live — modest added value against an already rich annotation 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?

Two sentences, zero filler: the first delivers the outcome and returned fields, the second delivers the selection condition. Front-loaded and appropriately sized for a trivial lookup.

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, but the description compensates by naming the three returned fields, and with no parameters and full annotation coverage there is nothing else an agent needs to call it correctly.

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

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

The tool takes zero parameters, so there is nothing to disambiguate; 4 is the baseline for a no-parameter tool. The description does not misrepresent any input and correctly implies no arguments are needed.

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 ('Lekéri a ... banki átutalási adatait') and enumerates exactly what is returned: beneficiary name, account number, bank address. That enumeration separates it cleanly from the sibling get_shop_contact_info, which covers other shop data.

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 an explicit trigger condition: use when the customer wants to pay by advance bank transfer and asks for the account number or transfer details. It does not name a sibling to avoid or state exclusions (e.g. what to use for card payments), so it falls short of a 5.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile needs no restating. The description usefully adds the corpus scope (which classes of documents live here) but says nothing about behavior on an unknown or unmatched topic, nor whether the answer is free text or a list of entries.

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 that front-loads identity (official knowledge base / FAQ of the shop) before the content list and the topic filter. It is dense but every clause carries information; only the enumeration of document classes runs slightly long.

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

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

With one required parameter, full schema coverage and rich annotations, the description covers what content lives here. Because there is no output schema, the description should have said what a response looks like (single answer vs multiple articles) and what happens when the topic is unknown, which it does not.

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%, and the schema already explains that topic is a key from the system-prompt topic list with examples ('szallitasi_ido', 'adatvedelem') or a free-form subject. The description only echoes that retrieval is topic-based, adding no format, casing, or fallback guidance 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?

States a concrete verb and resource: it retrieves ("kérhetők le") entries from the shop's official knowledge base / FAQ, enumerating the content classes (general policies, production rules, regulations, customer information) filtered by topic. This is clearly distinguishable from the narrow sibling getters (bank details, price, contact info), though it never says explicitly which sibling wins when topics overlap, e.g. shipping time vs get_shipping_info.

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: consult this endpoint for general operational guidance, manufacturing rules and policies, selected by a topic key. There is no explicit when-to-use/when-not statement and no named alternative, which matters because get_shipping_info, get_shop_contact_info and get_bank_details plausibly overlap with FAQ topics like shipping or 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 readOnly, idempotent, non-destructive, so safety needs no restating. The description adds real behavioral context: it reads price AND stock, requires a product_id sourced from prior conversation history, and rejects custom-dimension bricks. It doesn't describe failure behavior when the variant or size combination is unknown, which keeps it below a 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?

Front-loaded with the action and scope, then the prerequisite, then the exclusion — a sensible order. Three sentences with no filler; the bolded caps are intentional emphasis rather than noise, though the double emphasis slightly clutters the read.

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?

Covers purpose, prerequisite, exclusion, and what is returned (price and stock), which is adequate for a read-only lookup with no output schema. What's missing is behavior for the required-but-possibly-absent product_id conflict and any note on how selected_attributes must match get_product_schema output beyond the schema text itself.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds one genuinely useful fact (product_id is read from a hidden note in history), but it also asserts product_id is KÖTELEZŐ while the schema says 'Ha nem tudod, hagyd üresen!' and only selected_attributes is required — this conflict is not resolved in the description, so it doesn't reliably add parameter clarity.

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 ('Lekéri a kiválasztott termékváltozat pontos árát és készletét') and positions the tool in a workflow ('Második lépés a normál termékek árazásához'). It explicitly warns it must not be used for custom-sized products, naming the sibling calculate_custom_cuboid, so an agent can distinguish it without opening schemas.

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 an explicit when-not ('TILOS ezt meghívni egyedi méretű téglatestre/tömbre') paired with the correct alternative ('arra a calculate_custom_cuboid való'), plus the precondition that product_id comes from a hidden note in history. Both routing and prerequisites are stated, not left 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 declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds useful behavioral context beyond that: it returns the mandatory parameters of a selected product, operates in two alternate modes, and is a prerequisite step for downstream search/pricing. It stops short of saying what happens when a keyword yields no match.

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, front-loaded with the core purpose and ending on the exception, which is the right place for it. Dense but slightly cluttered by exclamation marks and all-caps emphasis that add tone rather than 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 read-only lookup with rich annotations and full schema coverage the description is sufficient to select and invoke the tool. But with no output schema, the agent still gets no picture of the return shape (product data vs. a parameter set) or the no-result behavior, which is a meaningful gap for a prerequisite lookup 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% and both parameter descriptions already state the either/or relationship (product_id makes product_name unnecessary) and the keyword constraint. The description mirrors that at a higher level but adds no syntax, format, or edge-case detail beyond the schema, so 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?

States a specific verb (retrieves) and resource (product/category data), and explicitly frames itself as the first step of product lookup. The two operating modes (keyword search vs. exact ID lookup) are named, and the exception tool is called out by name, so an agent can distinguish it from siblings immediately.

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 sequencing guidance ("first step for product search") and an explicit exclusion routing custom-sized cuboid pricing to calculate_custom_cuboid. However, it does not clarify the relationship with the sibling get_product_price (e.g., whether to call this before or instead of the price tool), leaving one relevant alternative undifferentiated.

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 read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds value beyond them by disclosing the returned payload contents (fee tables, surcharge tiers, merge rules) even though no output schema exists.

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

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

Two sentences, front-loaded with the resource and its contents, then the usage note. The long enumerated clause is dense but every item listed is substantive; minor trim possible on the courier-name parenthetical.

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 by listing fee categories, surcharge structure, payment methods, and merge rules. Nothing an agent needs to decide or call 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 there is nothing to disambiguate and the baseline applies. The description correctly does not waste space on argument 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?

Specific verb + resource: it returns the shop's current shipping and payment options, and then enumerates exactly what is inside (courier base fees for MPL/GLS/Posta, COD tiered surcharges, payment methods, free order-merge rules). This clearly separates it from siblings like get_product_price, get_bank_details, and get_faq_answer.

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 final sentence gives clear usage context: extract exact fees and conditions from the returned JSON to build the answer, which tells the agent when to reach for it. It stops short of naming alternatives or exclusions (e.g. when to prefer get_faq_answer for policy questions), so it is not a full 5.

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

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

While the annotations clearly mark the tool as safe (ReadOnly, Non-Destructive), the description reinforces its purpose as a lookup function, adding context without contradicting the existing safety hints. However, it does not describe specific return formats or error handling.

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 highly efficient. The first sentence defines the scope (what it does), and the second provides the trigger for use (when to use it). It uses minimal wording to achieve maximum clarity.

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 lookup tool, the definition is very complete. It answers the 'what' and the 'when' (usage), and the annotations cover the 'how safe.' No critical operational gaps remain.

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?

Since the schema contains zero parameters (100% coverage), the description does not need to add semantic meaning to inputs. The baseline score of 4 is applied, acknowledging that the description's job of defining parameters is irrelevant 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?

The description clearly and specifically states the resource being retrieved: the webshop's official customer service contact details, including phone, email, and website. This is distinct from all listed sibling tools like get_product_price or get_shipping_info.

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

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

It provides explicit usage context: 'Use this operation when the buyer is interested in the store's phone number, email address, or customer service contact options.' This gives the agent clear behavioral instructions.

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