Проект ПРОФТЕХПОЛ — промышленные полы (Москва и МО)

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

With no annotations, the description carries the full burden and does disclose real side effects: an engineer telephones the customer, the lead enters the site pipeline (Telegram + CRM), and anti-spam filtering applies. It stops short of failure/duplicate handling, idempotency, or what the caller sees if spam protection rejects the lead, which are the remaining 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?

Three tight sentences: purpose first, the hard usage constraint second, the routing/side-effect context third. No repetition of schema content and 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 mutating tool with zero annotations and no output schema, the description supplies the purpose, the strict invocation condition, and the downstream effect (callback + CRM entry), which is enough to call it correctly. What is not covered is outcome/error behavior — e.g. suppression by the spam filter or duplicate submissions — which an unannotated write tool would ideally mention.

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% — each of city, name, phone and request already has type, optionality and format guidance (e.g. 11 digits starting with 7, request up to 700 characters). The description only implies that phone is the user-provided required field and adds no format or validation detail 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 verb and resource ('создайте заявку на расчёт промышленного пола') plus the concrete consequence (an engineer calls the customer back). Against a sibling set that is entirely read-only lookups (faq, find_cases, get_facts, get_service, list_geo, list_services), it is unmistakably the single creation/lead tool, so an agent can route to it without opening any schema.

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

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

Gives an explicit gating rule — 'Use ONLY when the user themselves asked to leave a request and gave their phone' — and names the required precondition (user-initiated request plus phone number). When-to-use and when-not-to-use are both stated, leaving nothing 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?

No annotations are provided, so the description carries the full burden. It discloses the corpus size and the query/no-query branching behavior, but does not state that this is a read-only lookup, whether results are paginated or capped, or how relevance is determined — gaps that matter given the absence of 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?

Two sentences, no filler; the corpus scope is front-loaded and the query/no-query behavior follows immediately. Every clause earns its place.

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 explain returns, and it does distinguish the two response shapes (topic structure vs. relevant Q-and-A). Coverage is good for a read-only lookup; a note on result limits or the nature of the source material would complete 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?

Schema coverage is 100% with a single optional parameter, so the baseline is 3. The description adds genuine meaning beyond the schema: the same parameter switches the tool between returning the topic structure and returning matching questions/answers, which the schema's terse example string 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?

States a specific function (engineer's answers to frequent customer questions) plus the corpus scope (200 questions, 36 topics) and concrete subject areas. Nothing in the sibling set (find_cases, get_facts, get_service) is explicitly contrasted against, but the FAQ domain is unambiguous enough for selection.

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 explains the two invocation modes clearly ('without a query — topic structure; with a query — relevant Q-and-A'), which is useful behavioral guidance. It gives no explicit when-to-use-vs-alternative routing against siblings such as get_facts or find_cases, so guidance is implied rather than stated.

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 mostly succeeds: it discloses the dataset size (262 cases), the covered timeframe (since 2015), the return shape (name, area m², year, link), and the valid type values. It omits any note on pagination behavior or the max-50 cap, which the schema itself covers.

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 paragraph that front-loads the dataset scale and filters, then closes with the reason to use it. Every clause carries information, though the long type enumeration is somewhat list-heavy.

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, and the description compensates by listing the returned fields (name, area, year, link). For a simple three-parameter read tool this is close to complete; only pagination/limit behavior is left 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 baseline is 3, but the description adds real value by enumerating the domain values for 'type' (склад, производство, паркинг, автосервис, etc.) that the schema leaves as a bare string with no enum constraint. The 'city and/or type' phrasing also clarifies that filters combine optionally.

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 verb (find) and resource (cases/выполненные объекты) and scopes it with concrete attributes: 262 cases since 2015. It does not explicitly distinguish itself from siblings like get_facts or list_services, but the resource is 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?

The closing line 'доказательства опыта для проверки подрядчика' gives the business context — verifying a contractor's track record — which implies when to reach for it. However, it names no alternatives (get_facts, get_service) or exclusion conditions, leaving the agent to infer 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?

With no annotations, the description carries the full burden. It does disclose a genuinely useful behavioral trait: results come 'с указанием страниц-источников для проверки' (with source pages for verification), signaling that values are cited and auditable rather than free-form. It does not state permissions, caching/staleness, or the response shape, so the disclosure is partial.

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 sentence, front-loaded with the resource and then the returned fields. The field enumeration is long but each item is substantive, since it substitutes for a missing output schema. Minor redundancy from the colon-separated list but no filler sentences.

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, annotations, or parameters, the description is the only specification source, and it compensates by enumerating the returned fact categories and the fact that sources accompany them. That is close to sufficient for a static read-only lookup; only the exact response structure and any freshness guarantees 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?

The tool takes zero parameters, so there is no parameter semantics to document beyond the schema itself; the baseline for a no-argument tool is 4. The description correctly makes no parameter claims and instead spends its words on the return content.

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 (facts about the organization «Проект ПРОФТЕХПОЛ») and enumerates exactly which facts are returned: canonical name, legal entity, experience, number of completed objects, cities, warranty, office address. This distinguishes it from data-listing siblings like list_geo and list_services. It lacks an explicit contrast with the closest sibling, faq, which also covers organizational information.

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 enumerated fact categories — an agent can infer this is the tool for company metadata rather than service or geography lookups. However, there is no explicit when-to-use statement and no named alternative such as faq for question-shaped organizational queries, leaving the agent to infer the boundary.

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 behavioral burden. It does disclose the return contents (description, price guide, link, client FAQs) and a conditional ('если публичен' for the price), which is useful, but it says nothing about auth needs, missing-slug behavior, or error handling.

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 compact sentence that front-loads the core purpose and enumerates return contents without waste. Every clause earns its place.

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 no output schema and no annotations, the description enumerates the returned content well enough for an agent to know what to expect. It stops short of explaining the slug-to-list_services workflow explicitly, leaving a small 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 100% and the single slug parameter is well documented in the schema (including an example). The description only restates 'по slug' without adding format or validation details beyond the schema, so the baseline of 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 states a clear verb+resource ('Детально об одной услуге' — detail about a single service) and scopes it by slug, which distinguishes it from the sibling list_services. Sibling differentiation is implicit rather than explicit, and the mention of 'частые вопросы клиентов' creates some overlap with the faq tool without resolving it.

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 schema note that the slug comes from list_services hints at the natural flow (list first, then fetch details). There is no explicit when-to-use vs the faq or get_facts siblings, and no exclusions stated.

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 useful behavioral scope — the enumeration is fixed at 18 cities, limited to Moscow and the Moscow region, and includes per-city counts — but it says nothing about caching, freshness, ordering, or that the call is read-only and side-effect free.

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 padding, packing scope, coverage count, link presence, and per-city metric into one line. Dense but readable; a slightly clearer opening verb would improve it marginally.

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 and no output schema, the description must convey the shape of the return value, and it does: a fixed set of 18 cities with links and object counts. Minor gaps remain (ordering, whether non-Moscow regions exist in other tools), but the agent has enough to call and interpret 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 schema declares zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly frames the tool as a no-argument full listing rather than a filtered 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?

The description names the resource (работа cities / geo) and specifies what each entry contains: a geo-page link and a count of completed objects. It is specific enough to distinguish from siblings like list_services, though it never states the verb explicitly (the name 'list_geo' carries that).

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, when-not-to-use, or alternative-tool guidance. The agent must infer from the sibling set that this is the only geo/city-listing tool and is used for geographic coverage questions.

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