КМВ INFO — новости Кавминвод

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 and world-scope profile is fully covered. The description adds a genuine behavioral fact the annotations lack — the data covers the last 24 hours — but says nothing about freshness, source, or refresh cadence.

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 packs the four covered domains with no filler. It reads as a dense enumeration rather than a run-on of redundant clauses.

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 enumerated domains effectively tell the agent what comes back, and the default geography is covered by the parameter description. Only the freshness/source of the data is left unstated, which is a minor gap for a read-only status tool.

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

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

Schema description coverage is 100% and the single city parameter is documented in rich detail, including aliases and the empty-string default (Kavminvody and the region). The description adds nothing about the parameter, which is the expected baseline when the schema does the work.

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 (current city situation) and enumerates the exact content domains it returns: power/water/gas outages, emergencies and accidents, alerts, and fuel availability. That is far more specific than the sibling names events or latest_news, though it never explicitly names an alternative to route against.

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 phrase "что сейчас происходит" and the 24-hour window, which suggests a real-time local snapshot. It never states when to prefer this over events, latest_news, or search_news, nor any prerequisites.

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 the full safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the description does not need to restate safety. It adds the geographic and topical scope of the reads, but says nothing about result ordering, pagination behavior, or what an empty result means — useful behavioral context that is missing.

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 with no filler — the resource and scope come first and nothing is repeated from the name or title. Appropriately sized for a listing tool whose parameters are largely carried by 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 5-parameter, zero-required listing tool with no output schema, the description covers the domain adequately but omits the default window (today, +7 days by default via schema), the limit ceiling, and what the returned entries contain. Combined with annotations and a fairly rich schema it is minimally sufficient, but not complete.

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 60%: city, date_from and date_to are documented in the schema, while kind (13-value enum) and limit have no schema descriptions. The description's category list ('Концерты, спектакли, кино, выставки и праздники') loosely maps onto some kind enum values, adding a little meaning, but it leaves limit and the majority of enum values unexplained. Baseline 3 is 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?

The description names a concrete resource (concerts, plays, cinema, exhibitions, holidays) with geographic scope (КМВ cities and the края) and a date constraint, so an agent immediately knows this is an events/listing lookup rather than a news tool. It is clearly distinguishable from the news-oriented siblings, though it never names or contrasts 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?

There is no when-to-use or when-not guidance, no mention of alternatives such as search_news or city_situation, and no statement of prerequisites or edge cases. The phrase 'на выбранные даты' only vaguely implies the tool is date-scoped; nothing tells the agent when this tool should be chosen over its siblings.

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 and non-destructive, so safety is covered. The description adds genuine value by specifying what content the call surfaces (headline, date, city, source, full text), which is important 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?

A single front-loaded sentence naming the resource first, then the source of the url, then the returned fields. Dense but every clause carries information; no 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?

For a one-parameter read tool with full schema coverage and annotations handling the safety profile, the description supplies the missing return-content detail. No output schema exists, so enumerating fields is the right compensating move; only pagination/length behavior is unaddressed.

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 would be 3. The description goes beyond the schema by clarifying the url originates from other tools and accepts infokmv.ru links, adding origin context the schema alone does not convey.

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: retrieving the full text of a news article by infokmv.ru link, and even enumerates the fields returned (headline, date, city, source, text). This separates it from list-style siblings like latest_news or search_news, though no sibling is named 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?

It clearly indicates the context of use by stating the url comes from other tools' url field, implying this is a follow-up call after locating a news item. There is no explicit when-not guidance or named alternative, 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 readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety and side-effect questions are answered. The description adds the semantics of important=true (only items promoted to the «Главное» feed), which is genuine extra context, but says nothing about ordering, freshness windows, or result volume.

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, no filler, with the scope of the feed stated before the important flag caveat. 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?

For a five-parameter, all-optional news query with no output schema, the description covers what is fetched and the non-obvious flag. It leaves the limit cap behavior and the shape of returned items implicit, which is a minor gap given how conventional a news list 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 60%, and the description supplies the meaning of the one undocumented high-ambiguity parameter: important=true restricts output to top stories rather than merely ranking them. city, rubric and hours are already documented in the schema, and limit remains unexplained, so it is not fully compensating.

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 (последние новости КМВ и Ставрополья) and the axes of retrieval (по городу, рубрике и периоду), so an agent knows it is a filtered recency feed. It never distinguishes itself from the sibling search_news or get_article, so the agent must infer the split.

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 when-to-use, when-not, or named alternative, even though search_news and get_article sit in the same family and overlap heavily. The only guidance is the embedded note on important=true, which is a parameter behavior rather than usage 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 readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds one genuine behavioral fact beyond the annotations: results are limited to cities/regions that actually have news, and each entry carries a slug. No mention of ordering or whether the list is complete.

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 short sentence with the resource front-loaded and zero filler. Every clause (scope condition, returned field) 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 no output schema, the description must carry the return-value burden, and it only partly does: it names the entity type and the slug field but says nothing about the shape of the response (list vs object) or ordering. For a zero-parameter, read-only listing tool this is adequate but thin.

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. Per the zero-parameter baseline, no compensation is required.

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 (cities and regions) with a stated scope condition ('по которым есть новости') plus the returned field (slug), so the agent knows this is a discovery/lookup list rather than a news feed. It does not explicitly distinguish itself from siblings like city_situation, 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?

No when-to-use guidance and no alternatives named. The scoping phrase 'по которым есть новости' implies the result is a filtered lookup, but nothing tells the agent to call this to resolve slugs for other tools or when it should prefer city_situation.

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, so the safety profile is covered. The description adds genuinely new behavioral context: which fields are matched (headline, teaser, body) and the temporal boundary of the corpus. It still omits result ordering and how limit interacts with ranking.

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. The core capability is front-loaded in the first sentence and the corpus boundary follows as a separate, useful constraint.

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, but annotations carry the safety profile and the schema documents four of five parameters with formats and defaults. For a low-complexity search tool the description covers the essential framing; only result ordering and the meaning of limit remain 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 coverage is 80%, so the baseline is 3. The description reinforces that matching applies to words and dates and clarifies the matched fields behind query, but it adds nothing for limit (no schema description) or date inclusivity beyond what the schema already 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 (поиск) and resource (новости), plus the exact scope searched: заголовок, анонс, текст, and dates. The archive start date ('с марта 2026 года') implicitly separates it from latest_news, but no sibling is named 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?

Usage is only implied: the archive framing ('Архив — с марта 2026 года') suggests this is the historical-search tool as opposed to latest_news or events, but the description never states when to prefer it or when not to use it.

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