consultations

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

Annotations already cover read-only, idempotent, non-destructive, and openWorld behavior. The description adds valuable context: slots come from the live schedule and a no-data result returns available=false with booking links, guiding fallback handling. It does not cover auth or rate limits, but with annotations this is solid.

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 tight sentences, front-loaded with the purpose and immediately covering the fallback case. No 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?

An output schema exists, so return format need not be detailed, and annotations cover safety. The description includes the critical no-data behavior, making it adequately complete for invocation, though it omits sibling routing guidance.

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 six parameters are fully documented in the schema. The description adds no parameter-level meaning beyond the schema, 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?

States a specific resource (free consultation slots) and scope (next days, live schedule), making it clear it returns availability. It does not explicitly differentiate from sibling tools like get_consultation_details or prepare_booking_handoff, so it falls short of 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?

Provides a fallback action when no data is available (send the person to the booking page), which is useful usage context. However, it does not state when to prefer this tool over alternatives or any prerequisites, leaving usage 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 cover read-only, idempotent, non-destructive, and closed-world behavior. The description adds meaningful behavioral limits: only published details are returned, unknown age/couple format/payment methods/approach are not inferred, and no clinical suitability assessment is made. These are substantive caveats beyond the structured metadata.

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 purpose before the caveats. The second sentence is dense and grammatically awkward ('Unknown age, couple format, payment methods and approach are not inferred'), but every sentence contributes relevant information without filler.

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?

Because an output schema exists, return values need not be explained, and annotations cover the safety profile. However, for a 1-parameter tool with 0% schema description coverage, the description should at least clarify the section enum values and give basic usage context; those gaps keep it only minimally adequate.

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 0%, so the description carries the burden of explaining the single 'section' parameter. It only says 'by section' and never clarifies what the enum values ('all', 'format', 'payment', 'cancellation', 'scope') actually return, leaving the agent to infer meaning from the schema alone.

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 ('published session details') and the filtering dimension ('by section'), but uses no explicit verb and does not distinguish this tool from siblings like get_services_and_pricing or get_practice_overview. An agent can infer it returns consultation details, but the boundary against other content tools is left to guesswork.

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

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

There is no when-to-use guidance and no mention of alternatives among the many sibling tools. The second sentence gives negative scope ('not inferred', 'no clinical suitability assessment'), which is useful boundary-setting, but it does not tell the agent when this tool should be selected instead of another.

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, so the safety profile is covered. The description adds a useful policy fact — that booking is only possible through the official calendar — which is context beyond the annotations, but it does not describe the shape or scope of what is returned.

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

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

Two short sentences, no filler, with the core content (the contact channels) front-loaded and the booking caveat following it. Every clause carries 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 an output schema present, return values need not be explained, and with zero parameters there is no input complexity to cover. The description supplies the essential content and a booking constraint, though it could say more about when this list is the right answer.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-parameter tool is 4. Schema coverage is also reported at 100%, leaving no gap.

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 (contact channels: email, Telegram, booking page) so an agent can tell it is a 'list the ways to reach the practitioner' tool. It does not explicitly contrast itself with siblings like prepare_booking_handoff or get_available_slots, but the second sentence hints at the booking 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?

Usage is only implied — an agent can infer it applies when the user asks how to make contact. The line 'Booking happens only via the official calendar on the site' is a mild routing signal away from booking tools, but there is no explicit when-to-use or when-not-to-use statement.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered. The description adds real behavioral context beyond them: answers are the practitioner's own words, verbatim, and are in Russian — the language detail is materially useful for an agent deciding whether the content fits the user's locale.

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

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

A single front-loaded sentence naming the resource, the fidelity of the content, the language, and the topic scope. Every clause carries information; nothing is padded.

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?

An output schema exists, so return structure needn't be described, and the topic enumeration tells the agent what coverage to expect. The only minor gap is that it doesn't say whether the FAQ is static or refreshed, which is low-impact for a read-only lookup.

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 clarify and the baseline is 4. No param syntax or format guidance is 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 resource ('frequently asked questions with the practitioner's own answers') and enumerates the covered topics, so the agent knows exactly what content comes back. It does not name or differentiate itself from the many sibling get_* info tools, though the topic list implicitly separates it from get_available_slots or get_services_and_pricing.

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: an agent can infer it should call this for general practice questions (fit, rhythm, booking, cancellations). No explicit when-to-use condition, prerequisites, or alternative tool is named, so the routing decision is 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 genuinely non-obvious context — the content is verbatim from the site and is in Russian — which an agent could not learn from structured fields. It stops short of noting stability or formatting, so 4 rather than 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?

Two short sentences, both earning their place: one identifies the content and its language, the other states the use case. The most decision-relevant information is front-loaded.

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 an output schema present, the return value needs no explanation, and with no parameters and full annotation coverage the remaining burden is small. The description supplies the two facts an agent actually needs: what the content is and when to consult 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 zero parameters, so per the rubric the baseline is 4. There is nothing for the description to document, and it introduces no misleading parameter expectations.

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 identifies the resource precisely — the verbatim list of concerns clients bring — and situates it in the consultation practice. It is clear enough to distinguish from siblings like get_faq or get_services_and_pricing, though it never states a verb (e.g., 'retrieves') and relies on implied action.

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 condition for use: 'Use it to judge whether a request matches this practice.' That is a real decision rule, not just a restatement. It names no alternative tool, however, so an agent must infer when a different sibling is preferable.

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 non-destructive/openWorld=false, so the safety profile is fully covered structurally. The description adds no further behavioral context such as caching, freshness, or scope of the 'website' beyond the content list, so it meets but does not exceed the lowered bar.

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 tightly written sentences: the first enumerates content, the second gives the routing instruction. No filler, and the 'call this first' guidance is appropriately placed at the end as an actionable directive.

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 an output schema present, the description needn't explain return values, and it does not. For a no-parameter, read-only grounding tool, the description covers what an agent needs to decide when to call it and what it will learn.

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

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

Zero parameters, so the baseline is 4. The description usefully frames what the tool surfaces (provider, service, limits, language, canonical links), which functions as an implicit description of the returned content even though there are no inputs to document.

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 (site/practice overview) and enumerates the exact content it returns: provider identity, service description, limits, language, and canonical links. This clearly separates it from siblings like get_faq, get_services_and_pricing, and get_contact_options, which each cover narrower slices.

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?

Explicitly says 'Call this first to ground any answer about the practice,' giving a clear ordering rule that positions it ahead of the other sibling tools. It stops short of naming when NOT to use it or which specific sibling supersedes it for narrower questions.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context not in the structured fields: personal notes remain on the user's device and are neither read nor submitted, which bounds what the tool touches. Return values are covered by the output schema, so no further disclosure is required.

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, zero padding, with the substantive content front-loaded ahead of the privacy clarification. Every clause carries information an agent cannot get from the schema or annotations.

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

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

With no parameters, full annotation coverage, and an output schema describing the return shape, the remaining burden on the description is small and it discharges the main privacy concern. The one gap is routing guidance against the many sibling content tools, which keeps this from a 5.

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 the schema leaves nothing to explain and the baseline is 4. The description appropriately says nothing about arguments rather than inventing them.

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 content specifically ('published questions, topics and practical rules before a session'), which is more than a restatement of the tool name. It lacks an explicit verb, but the resource is identifiable and distinct from content-oriented siblings like get_faq and get_practice_overview. No sibling is named as the alternative, so it stops short of 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?

There is no explicit statement of when to use this tool versus alternatives such as get_faq, get_practice_overview, or get_inquiry_topics. The phrase 'before a session' implies a pre-session context, but the agent must infer that this is the prep-material tool rather than a general FAQ tool. No when-not guidance is offered.

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 a safe, idempotent, non-destructive read, so the description's added value is the domain context: prices are in EUR and sessions are conducted in Russian, both of which materially affect how the agent relays the result. It says the content is 'verbatim from the site,' signaling authoritative first-party text, though it gives no freshness or caching caveats.

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 compact clauses, front-loaded with the payload (what fields are returned) followed by the qualifiers (currency, language). No filler or repetition.

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?

An output schema already exists, so the description need not explain the return shape, and a no-argument informational tool has no invocation pitfalls to document. Content, currency, and language are all covered, leaving nothing an agent needs 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool is 4.

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

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

The description names a specific resource and enumerates exactly what it returns (session format, duration, price, and payment/reschedule/no-show rules), which is more informative than a bare 'get services' label. It does not explicitly contrast itself with the neighboring get_consultation_details or get_practice_overview, so sibling differentiation is left to 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?

Usage is only implied: an agent infers it should call this when a user asks about pricing or booking policy. There is no explicit when-to-use, no when-not-to-use, and no named alternative (e.g. get_consultation_details) for related requests.

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 openWorldHint, so the safety profile is covered. The description adds genuine non-redundant context: it explicitly disclaims reservation and message sending, and notes that a supplied start is validated against the live schedule, which is the key behavioral detail an agent needs.

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 compact sentences, outputs front-loaded, and the negative scope constraint placed second where it belongs. No filler and nothing repeated from the schema or annotations.

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

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

An output schema exists, so return values need no explanation, and all parameters are optional, lowering the cost of under-specification. What is delivered (what is prepared, what is not done, schedule validation) is sufficient for correct invocation, though the undocumented timezone parameter is a residual 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 description coverage is 0% across three parameters, so the description carries the full burden. It hints at locale ('language') and start_at ('selected start') but gives no format, enum values, or effect for either, and timezone is not mentioned at all — half the parameters remain semantically opaque.

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 concrete verb ('Prepare') and enumerates the outputs (price, language, cancellation rules, official calendar link), which tells an agent exactly what this tool assembles. It is distinguishable from the sibling getters (get_available_slots, get_services_and_pricing) because it bundles them into a handoff, though it never says so 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?

The clause 'Does not reserve a slot or send a message' usefully bounds the tool's scope and the note that an optional start is checked against the live schedule implies when to pass start_at. However, it never names an alternative tool or states the condition under which an agent should prefer this over get_available_slots or get_services_and_pricing, leaving 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 safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real behavioral context: it returns exact text plus canonical sources and must not receive personal history. The privacy constraint is valuable, though the limited result set (limit max 8) is not disclosed.

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 dense sentence that front-loads the core action before the caveats. It packs three ideas (search scope, return content, privacy warning) without padding, though the sentence is somewhat run-on.

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?

An output schema exists, so return values need not be detailed, yet the description still summarizes them (exact text, canonical sources). The main gap is the undocumented limit parameter and the absence of explicit sibling routing.

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 only 33%, with locale documented in the schema and query/limit undocumented. The description clarifies that query is a short topic and that locale defaults to ru, which partially compensates, but the limit parameter (1-8) is never explained in either place.

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 (Search) and resource (already published FAQ answers) with a scoping constraint (short topic, Russian or English). It is distinguishable from the sibling get_faq, though the distinction is implied by 'search' rather than stated 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 an implied usage context ('short topic', 'already published') and one explicit exclusion ('do not send personal history'), but never says when to use this instead of get_faq or get_inquiry_topics. Usage is inferable, not spelled out.

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