Katalog Artistov — artists for events

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds a real behavioral fact not present in structured data: contact details are deliberately withheld. It stops short of saying what happens if both url and slug are supplied, or any rate/pagination 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 with no filler; the returnable-field list is front-loaded and the limitation plus alternative follow immediately. The field enumeration is long but each item earns its place by describing the payload.

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 usefully takes on the job of describing what comes back and explicitly carves out what does not (contacts). The remaining gap is input-side: with required=0 and no guidance on whether url or slug is preferred, an agent has to infer that at least one must be supplied.

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 both parameters are already documented (url as a katalog-artistov.ru card link, slug from search_artists). The description adds nothing about their relationship, mutual exclusivity, or precedence, 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?

The description enumerates the exact contents of the returned card (description, genre, city, lineup, repertoire/skills, tags, photos, video presence, fee guideline, link), which makes the resource and scope unmistakable. It also implicitly distinguishes itself from request_quote. The verb itself ('get') is not stated, but the field inventory is specific enough that an agent knows what it retrieves.

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 exclusion and routes to the alternative: contacts are not returned, and pricing/free-date questions must go through request_quote. What it does not say is when to reach for this versus search_artists (e.g., call this after a search result to hydrate details), so the routing is clear only for the quote case.

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 fully covered by structured data. The description's only addition is enumerating the returned fields, and it says nothing about freshness, size, or stability of the category set. Adequate but not rich, hence a 3.

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 that names the resource first and the consuming tool last. Dense but every clause carries information; 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?

With no parameters, no output schema, and annotations covering the safety profile, the description supplies what is missing: the returned field names and the purpose (search_artists filters). Complete enough for an agent to invoke it correctly, though it could note how often the catalog changes.

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 baseline for parameterless tools a 4 applies. The description does not need to explain any parameter syntax and correctly does not attempt to.

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 and its two halves: catalog genres (with returned fields slug/name/artist count/link) and collection-tags (repertoire, languages, event types). An agent can tell it apart from search_artists (consumer of this data) and get_artist. It is not explicitly differentiated from list_cities, the other list_* sibling, which keeps it from 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?

It gives a clear purpose: the output feeds the filters of search_artists, which effectively tells the agent when to call it. There is no explicit when-not or stated alternative, but the context is unambiguous.

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, closed-world behavior, so the safety profile needs no restatement. The description's added value is the shape of the returned payload (slug, name, artist count, link), which matters because there is no output schema, but it says nothing about ordering or result size.

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 fragment with no filler; the resource is stated first and the payload fields follow. It is terse but not ambiguous, though the list-style phrasing is slightly clipped.

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 listing tool whose annotations fully cover safety, the description supplies what the missing output schema would have: the fields each city entry contains. Only ordering/size expectations are unstated, which is minor here.

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

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

The tool takes no parameters, so the schema has nothing to document and there is no parameter semantics to get wrong; baseline 4 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?

Names a specific resource (cities of the catalog) and enumerates the returned fields (slug, name, artist count, link), so the agent knows exactly what it gets back. It does not explicitly distinguish itself from siblings, though no sibling appears to return cities.

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

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

There is no when-to-use or when-not-to-use guidance and no mention of alternatives such as list_categories or search_artists. Usage is only inferable from the noun 'cities'.

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 only declare the generic profile (not read-only, open-world, idempotent, non-destructive). The description adds genuinely new operational traits: the consent requirement, the callback SLA, and a hard rate limit of 3 requests per day — information an agent cannot infer from annotations.

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

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

Three compact sentences: purpose first, then prerequisites and consent, then the follow-up behavior and rate limit. No filler and nothing buried.

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 an 8-parameter mutation with no output schema, the description covers the essential unknowns: required inputs, consent, response behavior (phone callback), and volume limit. It stops short of noting the industry audience (Russian-language, Russian phone format), but nothing needed to call it correctly is missing.

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

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

Schema coverage is 100%, so the per-field meaning is already documented. The description still adds value by emphasizing which fields are mandatory and the consent precondition attached to them, slightly above the baseline for fully documented schemas.

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 outcome: sending the agency a request to learn the exact fee and free date, for one artist or a lineup. This clearly separates it from the read-only sibling tools (search_artists, get_artist, list_*), though the differentiation is implied rather than named.

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 concrete operating context: name and phone are required, the agent must ask for and obtain consent to share them, the agency calls back within one business day, and a max of 3 requests per day applies. It doesn't explicitly name which sibling to use first for artist lookup, but the 'slug артиста из search_artists' reference in the schema closes that gap.

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 new behavior: the result ordering ('рекомендованные каталогом, затем по популярности') and the concrete card shape, which an agent cannot infer from annotations. It does not discuss pagination limits beyond what the schema states.

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: purpose, return payload, ordering, then the hand-off to get_artist. The most decision-relevant facts (scope and result shape) are front-loaded and nothing is redundant.

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 compensates by enumerating the returned fields (slug, name, genre, city, fee-from, video, description, photo, link), which is what an agent needs to trust the result. For a 9-parameter tool it leans on the very complete schema for filter semantics, leaving only minor gaps around pagination behavior and result-set completeness.

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 enums, ranges and usage hints (page cap, city matching touring artists, slugs from list_cities/list_categories), so the schema carries the parameter burden. The description only restates the 10-card ceiling rather than adding filter semantics, making baseline 3 appropriate.

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 по каталогу... артистов по словам и фильтрам') and bounds the result ('Возвращает до 10 карточек'). It also distinguishes itself from get_artist by deferring detail lookups there, so an agent can separate the search tool from the detail sibling 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?

Clear about the search context (words + filters) and explicitly routes to get_artist for details, which is the most likely alternative an agent would confuse it with. It gives no explicit exclusions for the other siblings (list_categories/list_cities for slug discovery, request_quote for booking), so it stops short of full when/when-not guidance.

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