Brisket Eat & Fun

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

No annotations are provided, so the description carries the full burden. It discloses the kind of content returned (formats, capacity, conditions, links), which is the main behavioral trait for a static info getter. It does not explicitly say the operation is side-effect-free or requires no auth, though the 'get_' prefix and zero-param schema imply it.

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 content list is front-loaded in the first clause, and the submit_inquiry pointer is useful. The bilingual duplication (Russian then a shorter English restatement) is somewhat redundant but arguably serves discoverability and costs little.

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, zero-parameter, read-only info getter with no output schema, the description covers the content scope and the follow-up path (submit_inquiry) sufficiently. An agent could call this correctly without more information.

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 0 parameters, so the baseline is 4. Nothing in the schema needs explaining, and the description does not waste space on parameters.

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 content domain (banquets, corporate events, celebrations) and lists what it returns: formats, capacity, conditions, links, and inquiry instructions. This makes it distinguishable from get_restaurant_info, get_hours, and get_specials. The verb 'get' is only implied by the tool name, not stated in the description, which keeps this from being a 5.

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

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

Usage is implied by the topic: an agent should call this when a user asks about banquets or events. The description also routes to the sibling tool submit_inquiry for the follow-up action. It gives no explicit when-not guidance or comparison with other info getters, so it stays at implied usage.

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?

With no annotations, the description carries the burden and discloses key behavioral traits: timezone (Europe/Moscow), 24-hour format, entities covered, and different outputs depending on date presence. It does not specify return structure or handling of invalid dates, but for a simple read tool it is largely transparent.

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 short and front-loads the resource and scope. The bilingual repetition adds minor redundancy but supports localization; every sentence contributes useful 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 single-parameter read-only tool with no output schema and no annotations, the description provides sufficient context: what is returned, timezone, format, and date-dependent behavior. Minor gaps like invalid date handling are not critical for correct invocation.

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 meaning beyond the schema by clarifying that without a date the tool returns today's hours, whether it is currently open, and the whole week—schema only mentions today and the week, not open-now status.

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

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

The description states a specific resource (opening hours) and scope (hall, kitchen, bar) with timezone and format. It clearly distinguishes this from sibling tools like get_menu or get_restaurant_info, which cover different restaurant 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?

It explains behavior with and without the optional date parameter (specific day vs today/open-now/week), giving clear usage context. There is no sibling that duplicates this function, so no explicit alternative routing is needed, though no when-not-to-use guidance is provided.

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?

No annotations are provided, so the description carries the full burden. It discloses that availability is conditional, but it says nothing about what is returned, whether the lookup is read-only, or how a missing kids menu is signaled.

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 the availability caveat front-loaded; nothing is wasted. The bilingual duplication adds a little length but does not obscure the core statement.

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 zero-parameter lookup with no output schema, the definition gives the essential scope and the conditional-availability caveat. It could say more about the expected return content, but the core calling decision is covered.

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. The description correctly does not invent parameter semantics, matching the baseline for parameterless tools.

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 (kids menu) and scope (conditions for guests with children), which is clear enough for an agent to select it over get_menu. It does not explicitly say how it differs from the general get_menu tool or whether it is a subset lookup.

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 parenthetical 'if the restaurant has one' implies a usage condition (only call when the venue may offer a kids menu), but it does not contrast with alternatives such as get_menu or search_menu. Usage is implied rather than prescribed.

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?

No annotations are provided, but the tool takes zero parameters and reads static program information, so the absence of side effects is self-evident. The description still says nothing about whether the answer is static or account-specific, or what form the response takes, leaving moderate behavioral gaps.

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 fragments, front-loaded with the domain noun, with no filler. The bilingual duplication ('Клуб друзей / программа лояльности … Loyalty club info') is slightly redundant for a description this short but aids matching in both languages.

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

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

For a zero-parameter, no-annotation information lookup with no output schema, the description covers enough: it tells the agent what topics are answered (terms, tiers, enrollment). A note on whether enrollment steps are actionable or informational only would close the remaining gap.

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

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

The input schema has zero properties, so there are no parameters whose semantics need explaining; baseline 4 applies. The description correctly implies this is an unfiltered, no-argument lookup.

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 (loyalty / 'Клуб друзей' program) and enumerates the content it returns: terms, tiers, and how to join. None of the siblings cover this topic, so an agent can route to it without opening the schema, though the tool is never explicitly contrasted with alternatives.

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 listed content ('условия, уровни, как вступить') implies the questions this tool answers, which is enough to infer usage for a loyalty lookup. However, there is no explicit when-to-use statement, no prerequisites, and no mention of what to call instead for adjacent questions such as reservations or contact details.

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?

With no annotations, the description carries the full burden, and it does disclose real behavior: prices come from the register, include VAT, and alcohol is flagged 18+. It doesn't cover what happens if an unknown section name is passed, whether data is cached, or whether auth/locale constraints apply.

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 what the tool returns, then the argument behavior, then the alcohol caveat — no filler. The only cost is the bilingual duplication, which is a reasonable trade for Russian-language data but does repeat 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?

For a one-optional-parameter read tool with no output schema, the description tells the agent what it gets (sections overview vs section items), currency, VAT inclusion, and the 18+ marker — enough to call it correctly. Missing only edge-case behavior for an unrecognized section.

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 schema already documents the single optional 'section' parameter with concrete examples ('бар', 'коктейли', 'горячее', 'десерты', 'детское'). The description only echoes the no-argument vs with-argument behavior, adding no new 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 the resource plainly — the menu with RUB prices from the register, including VAT, and notes alcohol is marked 18+. That is more than a restated name, but it doesn't name the sibling tools it competes with (get_kids_menu, search_menu, get_specials), so an agent must infer the boundary.

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 invocation guidance for the optional argument: no argument returns a menu/section overview, with 'section' returns that section's items. It says nothing about when to prefer this over search_menu for specific dishes, get_kids_menu for children, or get_specials for promotions — the distinctions are 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?

With no annotations, the description carries the behavioral burden. It helpfully discloses conditional availability ('if the restaurant has one'), signalling the result may be absent, but it does not say whether the absence yields an empty result or an error, nor anything about return shape.

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?

Short and front-loaded on the resource. The bilingual Russian/English duplication roughly doubles the length for the same content, which is mild redundancy rather than bloat.

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 description does useful work by naming the payload (link, conditions, phone) and flagging that it exists only if the restaurant offers delivery. Only the empty/absent-result behavior 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 schema has zero parameters, so there is nothing for the description to disambiguate. Baseline of 4 applies for a no-argument tool whose inputs are fully determined by context.

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: delivery/takeaway ordering link, plus the conditions and phone number that accompany it. It is clearly separable from siblings like get_reservation_link or get_restaurant_info by topic, though no explicit verb frames the retrieval.

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

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

Usage is only implied by the resource name – an agent infers 'call this when the user wants delivery or takeaway'. There is no explicit when-to-use, no exclusion, and no named alternative (e.g., get_reservation_link for dine-in booking).

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?

No annotations are provided, so the description carries the burden. It usefully discloses that there is no deep link for a date and that the guest selects date/time on the page, plus what is returned (page/widget and phone). It does not address permissions or return shape beyond that, which is acceptable for a simple read-only lookup 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?

Content is front-loaded and efficient, spanning only a few sentences. The closing English gloss 'How to reserve a table' repeats the opening Russian phrase, which is minor redundancy but does not bloat 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 1-param, 100%-covered lookup with no output schema and no annotations, the description conveys what it returns (page/widget and phone) and its key limitation (no date deep link). Sufficient for an agent to call it correctly, though the exact return format is only loosely sketched.

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 schema already explains that the optional date param is for checking opening hours. The description reinforces that the date does not produce a deep link, adding mild clarity. Baseline 3 applies since the schema does the heavy lifting.

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 the resource clearly: booking page/widget and phone for reserving a table. It also distinguishes itself from a hypothetical date-specific link by saying no deep link exists. However, the name 'get_reservation_link' and the disclosure that there's no per-date link create slight tension, though the intent (how to reserve) is legible.

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 by 'How to reserve a table' — an agent can infer this is the tool to answer reservation questions. But there is no explicit when-to-use/when-not framing, and no siblings (e.g. get_order_link) are named as alternatives. Implied only.

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?

No annotations are provided, so the description carries the full burden. It does disclose the returned data shape (a flat fact sheet), and 'get' implies a read-only operation, but it says nothing about how the restaurant is identified with zero parameters, what happens if no restaurant context exists, or whether missing fields are omitted or nulled.

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 content is front-loaded and short, but the entire field list is duplicated verbatim in Russian and English, so roughly half the text is redundant rather than additive. A single bilingual sentence or one language would carry the same 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?

No output schema exists, so the description must convey return content – and it does, listing eight facet categories. However, for a zero-argument tool it omits the critical detail of how the target restaurant is resolved (ambient context, configured tenant, etc.), which is the one thing an agent cannot infer from the schema.

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 schema takes no parameters at all, so the baseline of 4 applies. The description rightly spends no effort on argument explanation and instead describes what the parameterless call yields.

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+resource (get_restaurant_info) and enumerates the exact facets returned: address, metro, phone, website, cuisine, features, rating, links. That enumeration implicitly separates it from siblings like get_hours and get_menu, but it never explicitly says so.

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

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

Usage is only implied through the field list – an agent can infer this is the general-purpose profile tool, but the description never states when to prefer it over get_hours, get_menu, or get_banquets_and_events, nor any prerequisites for calling it.

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?

With no annotations provided, the description carries the full burden. It discloses the key filtering nuance: when a day is given, only offers active that day are returned, plus offers with no day binding. It does not explicitly state that this is a read-only lookup (though 'get_' implies it), nor does it describe return format or any auth/rate-limit behavior, which keeps it at an adequate but not rich level.

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 short and front-loaded, with the core resource named first and the day-filtering nuance immediately after. The closing English phrase 'Promotions and lunch offers' is somewhat redundant with the opening Russian text but does not materially harm conciseness.

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 one-parameter read tool with fully documented schema and no output schema, the description supplies the essential filtering behavior and resource scope. The main missing piece is explicit routing guidance against sibling tools, but otherwise an agent has enough 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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful semantics beyond the schema: when a day is supplied, the result includes both offers active on that day and day-agnostic offers. The schema's day description does not mention the day-agnostic inclusion, so the description genuinely supplements the parameter behavior.

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 clearly: promotions, business lunches, and special offers (Акции, бизнес-ланчи, спецпредложения). It does not state an explicit verb such as 'returns' or 'lists', and it does not differentiate itself from siblings like get_menu or get_kids_menu by name, but the resource is distinct enough for an agent to recognize it as the promotions lookup.

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

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

The description implies when the tool is relevant (looking for current promotions), but it never explicitly says when to use this tool versus get_menu, get_kids_menu, or get_banquets_and_events. The day-related sentence describes filtering behavior rather than usage guidance, leaving the agent to infer the appropriate context.

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?

With no annotations, the description carries the burden and does add real behavioral detail: AND-matching across all words, a hard cap of 15 results, and prices in rubles. It doesn't cover failure modes or empty-result behavior, but for a simple read-only search it is well above the minimum.

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 core verb and scope, then result limit and matching rule. Every sentence adds information; nothing is repeated from 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 one-parameter read-only search with no output schema, the description gives the key return characteristics (max 15 items, ruble prices). Minor gap: it doesn't describe which fields are returned or what happens with no matches, but the tool is simple enough that this is not critical.

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 query parameter already has examples, so baseline is 3. The description adds matching semantics ('all words must match') that the schema does not state, which is meaningful guidance for constructing a query.

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 ('Поиск ... позиций меню' / 'Search menu items'), and adds the scope detail that it searches both name and description. This clearly separates it from listing siblings like get_menu, get_kids_menu, and get_specials.

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?

Search semantics are implied by the verb, but the description never says when to use this instead of get_menu or get_kids_menu, nor any exclusions. An agent can infer it, but the routing guidance is not explicit.

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?

No annotations exist, so the description carries the full burden, and it does disclose the key behavior: consent is a hard gate ('без согласия заявка не принимается'), and the outcome is a callback from the restaurant. Legal basis (152-FZ) is surfaced. It does not cover idempotency, duplicate submissions, or what a rejection looks like to the caller, which keeps it below 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?

The critical gate is front-loaded in the first two sentences and the callback outcome follows immediately; every sentence is load-bearing. The trailing English sentence is largely a translation of the preceding Russian text, which is mild redundancy rather than 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?

With 8 parameters (4 required) and no output schema, the description supplies the two things an agent most needs that structured fields cannot: the consent prerequisite and the fact that submission triggers a phone callback rather than an immediate booking. Remaining gaps are minor (no note on duplicate prevention or failure response 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?

Schema description coverage is 100%, including the enum values, phone format and the company_website honeypot warning, so the schema already does the heavy lifting and baseline 3 applies. The description restates the consent gate rather than adding syntax or format detail beyond 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 and resource ('Отправить заявку ... команде ресторана') and enumerates the four inquiry kinds, so an agent immediately knows this is the sole outbound/submission action. It does not name any sibling, but since every sibling is a read-only get_*/search_* tool, the differentiation is still unambiguous.

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 hard precondition chain: call ONLY if the person asked to be contacted, provided name and phone, and consented to personal-data processing; states the request is rejected without consent. That is a when-to-use rule plus a when-not-to-use consequence, not an implied one.

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