SEMERO Express Delivery & Customs

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds real substance by enumerating what the static content contains (legal entity name, UACBR licence number, operating history, target client segments), which tells the agent this is a fixed informational snapshot rather than dynamic 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?

Two sentences with zero filler: the identity/content facts are front-loaded, followed immediately by the usage trigger. Every clause carries either identification or routing value, even the licence code and weight range.

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 parameters and no output schema, yet the description effectively previews the return content by listing the attributes the agent will get (licence, tenure, service scope, client types). An agent has everything needed to decide to call it and to know what kind of answer to expect.

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 closed (additionalProperties: false), so there is nothing for the description to disambiguate. Baseline of 4 applies for a correctly parameterless 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 a concrete resource (company profile: legal entity, licence, history, client base) and a clear question type it answers. It does not name the sibling tools it should be distinguished from, but its scope is specific enough that an agent can tell it apart from contact_semero or search_faq by inference.

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 gives an explicit trigger: 'Use when the user asks about the company, its experience, licence, services or who it serves.' That is a clear when-to-use condition. It offers no exclusions or explicit alternative routing, so it stops 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 it a safe, idempotent, open-world read, so the description is free to spend its words on calculation semantics: NBU rate of the calculation day, shipping excluded from the base, and the EUR 10,000 ceiling where different rules take over. It leaves the actual returned breakdown unexplained, which costs it a point given there is 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?

Two dense but front-loaded sentences: trigger first, then scope, threshold, and the exclusion/alternative. The bilingual glosses add length but earn it by matching the user's language. Minor redundancy between the 'goods value only' phrase here and in the schema.

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 read-only estimator with no output schema, the description covers audience, inputs, rate source, and the boundary where it stops applying. What is missing is any hint of the result shape (e.g., separate duty vs VAT lines) or the duty-free threshold logic, which an agent might want when explaining the estimate.

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 baseline is 3; the description nevertheless reinforces the non-obvious parts — goods value only, shipping excluded, EUR or USD invoice currency — and states the EUR 10,000 ceiling that the schema expresses only as a raw 10000000 maximum. It does not describe the date parameter's Kyiv-time default, but the schema does.

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 ('estimate Ukrainian import duty and VAT for an individual's personal express parcel') and explicitly contrasts itself with check_customs for companies. The parenthetical Ukrainian synonyms (мито, ПДВ, розмитнення) make the intent unmistakable against all nine siblings.

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?

Opens with an explicit trigger ('Use when an individual asks how much duty/VAT they will pay'), gives a hard validity bound (EUR 10,000 goods value, above which business rules apply) and names the alternative for the excluded case (check_customs plus a broker). Both inclusion and exclusion conditions are covered.

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, but the description adds substantial context: minimum chargeable weight 0.5 kg, volumetric divisor L×W×H/5000, chargeable = max(actual, volumetric), 5–7 day transit, customs/VAT excluded, and a promo code that appears only for parcels ≥15 kg and never for documents. It even mandates a caveat the agent must relay (price confirmed after document check, with contact channels) — behavior that cannot be inferred from structured fields.

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?

Purpose and currency are front-loaded, then weight rules, then exclusions, then the mandatory caveat — a sensible order with no filler sentences. It is dense and slightly overloaded with promo/contact detail, but every sentence carries operational 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?

With no output schema, the description still tells the agent what the result means (price in UAH, customs excluded, promo code included for ≥15 kg parcels) and what caveat must accompany the answer. For a 7-parameter read-only calculator this is sufficient to call and present results 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?

Schema coverage is 100%, so the schema already documents each field, but the description goes further by explaining how the optional dimension parameters combine into chargeable weight and how sub-0.5 kg weights are rounded up — semantics the schema does not express. It does not add anything for direction or countryCode beyond what the schema states.

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 (estimated price of international express delivery) with concrete scope: to/from Ukraine, door-to-door, in UAH. It also pre-empts confusion with the customs sibling by explicitly excluding duty/VAT/clearance, so an agent can tell it apart from calculate_customs_payments without opening either 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 explicit trigger phrasing ('Use when the user asks how much delivery costs / ціна, вартість... from or to a country') and defines applicability by weight band (documents up to 2 kg, parcels 0.1–70 kg, heavier on request). It stops short of naming the alternative tool for customs costs, relying on the exclusion sentence to imply that routing.

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 a safe, idempotent, closed-world read, so the description's job is scope and boundaries, which it delivers: it discloses differing behavior by recipient type, states the customs-value formula, and explicitly caps its competence ('Never determines HS/УКТЗЕД codes — SEMERO's customs broker does'). No contradiction with readOnlyHint.

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?

Purpose and scope are front-loaded in the first sentence, with branching detail after, and no filler sentences. It is somewhat dense — the UAH 5000 / 1 day brokerage figure is a detail that arguably belongs in the response rather than 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?

With no output schema, the description carries the burden of return content, and it does sketch what comes back per recipient type (rules for individuals, valuation/CPT/duty/VAT/permit guidance for companies). A small gap remains: it does not say how authoritative or static that content is.

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 the enum values are self-describing, so the schema already does the work. The description still adds genuine usage meaning by telling the agent to elicit the recipient (company vs individual) before calling and explaining that the answer branches on that 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?

States a specific resource and jurisdiction (customs formalities in Ukraine for DHL/FedEx shipments) plus the concrete questions it answers: clearance, declaration, documents, EUR 150 threshold. It also carves itself out from siblings by explicitly deferring payment estimation to calculate_customs_payments and HS codes to the broker.

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 explicit triggers (user asks whether a shipment will clear customs, whether a declaration is needed, what documents are required, EUR 150), names the alternative it is not (calculate_customs_payments for estimates), and prescribes a sequencing step: ask who the recipient is first.

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 this a safe, read-only, idempotent lookup, and the description adds genuinely useful behavior beyond them: business hours, online availability, and critically that SEMERO does not accept orders through AI so the client must write or call directly. That last constraint prevents an agent from attempting a transaction the tool cannot perform.

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 dense sentences: the first packs all actionable contact data up front, the second gives the use-case routing plus the no-AI-orders caveat. No filler and nothing that 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 static, zero-parameter contact resource with no output schema, the description supplies everything an agent needs to decide to call it and to relay the result. Nothing about the tool's contract is left 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 and the schema is a closed empty object, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly implies a no-argument call.

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 opens with a concrete resource (SEMERO contacts) and enumerates exactly what it returns: email, WhatsApp/phone, hours, and online availability. It is immediately distinguishable from siblings like calculate_price or check_customs, which compute things rather than surface contact channels.

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 gives clear trigger conditions — ordering, exact pricing, broker consultation, manager contact — which is unusually explicit for a contact tool. The only gap is that 'get an exact price' overlaps with the sibling calculate_price without stating which one to prefer when the user just wants a number.

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 this as read-only, idempotent, non-destructive, and closed-world. The description adds useful domain behavior beyond annotations: Kyiv hub customs clearance, three days free storage, address delivery, pickup, and local courier fallback.

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 front-loaded with the shipment process and then lists concrete usage scenarios. It is dense but every sentence contributes relevant information; minor improvement could come from breaking the semicolon-heavy first sentence into clearer structure.

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?

Given the tool has no input parameters and no output schema, the description provides enough context for an agent to know when to call it and what domain information it covers, including customs, storage, delivery, pickup, and local courier coverage.

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 has zero parameters, so parameter semantics are not applicable and the baseline is 4. The schema is empty and consistent with a purely informational 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 clearly states the tool's informational purpose: explaining how shipments move inside Ukraine, including customs clearance, storage, delivery, and pickup. It is specific about the process but does not explicitly differentiate itself from the sibling delivery_rules 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 gives clear usage triggers: where/how to receive a parcel, delivery to a specific city, pickup, storage, and delivery time inside Ukraine. It does not name when not to use it or point to an alternative sibling 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured fields. The description adds content-scope context (which categories of rules are covered) but says nothing about the form of the answer, e.g. that it returns static reference text rather than a computed quote. A 3 is appropriate given the annotations carry the behavioral burden.

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, purpose front-loaded, alternative routing second. The Ukrainian term parentheticals (накладна, інвойс) earn their place as query-matching cues rather than filler, though the sentence is somewhat dense.

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 output schema and annotations covering safety, the description supplies everything an agent needs to select and call it. The only residual gap is that it does not indicate whether the response is a static policy summary or per-destination rules, which matters given the worldwide scope claim.

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. The description correctly implies a parameterless lookup by not suggesting any filters or item identifiers.

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 (general shipping rules with SEMERO) and enumerates its scope: required information and documents (invoice, packing list), document vs parcel categories. It also explicitly contrasts with the sibling restricted_items, so an agent can distinguish it from restricted_items without opening either 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 an explicit trigger (user asks how to prepare a shipment or what documents are needed) and an explicit alternative routing rule ('For a specific item use restricted_items'). Both when-to-use and when-to-use-something-else are present.

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), and the description adds meaningful context beyond them: the four possible verdict categories and the critical caveat that absence from the list must not be reported as allowed. It stops short of saying how the verdict is returned (state only vs. rule text), which leaves a small gap for a 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?

Front-loaded with the action and scope, then the trigger, then the caveat — a sensible order with no filler. The parenthetical example list in Ukrainian is slightly redundant with the schema examples, but it earns its place by anchoring the trigger condition.

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 two-parameter read-only lookup with a high-coverage schema, the description supplies purpose, trigger, result categories, and the not-found safety rule — essentially everything needed to call it and interpret it. Only the precise shape of the returned verdict is left implicit, which is a minor gap given no output schema exists.

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 both 'item' (with its own examples) and 'lang' (enum, default). The description's item examples largely duplicate the schema and it says nothing about the lang parameter, so it adds only marginal meaning beyond structured fields — 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?

States a specific verb and resource: 'Check whether an item can be shipped to/from Ukraine with SEMERO', and names the basis (SEMERO's published rules). The enumerated outcome states (prohibited, needs approval, not shipped by SEMERO, usually allowed) make it trivially distinguishable from siblings like delivery_rules or check_customs.

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: 'Use when the user asks whether a specific item can be sent', with concrete Ukrainian examples. It also gives a when-NOT-to-conclude rule ('If the item is not in the list, do not say it is allowed — a broker check is needed'), though it points to a human broker rather than naming the sibling tool that should be called instead.

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, closed-world, non-destructive, so the safety profile is covered. The description adds real context beyond that: the shape of the return (questions, answers, source page links), the citation requirement, and an anti-hallucination constraint ('Do not invent answers beyond the results') that meaningfully shapes agent 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?

Two sentences, both front-loaded: the first covers what it does and returns, the second covers when to use it and the grounding rule. No filler, no repetition of the title.

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 compensates by naming the returned fields and the source-page citation. For a simple three-parameter read tool this is nearly sufficient; only the empty-result behavior and the uk/en default are left 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?

Schema description coverage is 100% with defaults, enum values and min/max already documented, so the schema carries parameter meaning. The description adds nothing about lang, limit, or query syntax — the topical list loosely implies language coverage but never states the uk/en options. 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 and resource (search SEMERO's published FAQ) plus the topical scope (delivery, customs, China/USA shipping, documents) and the return payload. The 'use first for general questions' clause partially separates it from specialized siblings like delivery_rules and check_customs, though it never names them explicitly.

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 activation context — use first for general questions in the listed domains — and a downstream obligation to cite the source page. It stops short of saying when to prefer a sibling tool (e.g. calculate_customs_payments for concrete cost figures) or what to do when no matches are returned.

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 read-only, idempotent, non-destructive, closed-world behavior. The description adds meaningful context beyond that: it returns a link only, does not fetch live status or location, and explains carrier booking constraints including the UPS situation in Ukraine. It does not describe the exact return shape, but that gap is minor for a link-returning 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?

The description is front-loaded with the core action and return value, then adds exclusion and carrier context. Every sentence contributes useful information, though the carrier caveat is somewhat dense and includes a parenthetical operational note. It remains efficient overall.

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 only two required parameters, full schema coverage, and annotations covering safety and idempotency, the description supplies everything else an agent needs: what is returned, what is not fetched, and how carrier options work. No output schema exists, but the description already states that the return value is a tracking page link.

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 both parameters are already documented by the schema itself. The description still adds real meaning for the 'carrier' parameter by explaining that SEMERO books DHL and FedEx while UPS and GLS links apply only to existing customer waybills. It adds no extra detail for 'awb' beyond the schema, so it falls short of a full 5.

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: 'Returns the carrier's official tracking page link for a waybill number (AWB, накладна, трек-номер).' It also explicitly excludes adjacent capabilities ('Does not fetch status or location'), which prevents confusion with a shipment-status tool. No sibling tool is similar, so the purpose stands alone clearly.

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 gives an explicit trigger ('Use when the user wants to track a shipment') and an explicit non-use case ('Does not fetch status or location; shipment statuses are emailed automatically'). The carrier-specific constraints further guide when the tool is appropriate for UPS/GLS versus DHL/FedEx waybills.

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