Saymon RU Data API

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

No annotations are present, so the description carries the full burden. It adds useful traits: rates are official, daily, refreshed once per day, and the tool costs $0.008 USDC. However, it does not disclose whether the call is read-only, what the response contains, or how missing or delayed rates are handled.

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 one dense sentence that front-loads the core resource and update behavior, then adds scope and pricing. Every part earns its place and there is 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?

Given the opaque schema and absence of an output schema, the description is not sufficient for reliable invocation: an agent still cannot tell how to construct the required `args` and `extra` objects or what the return value looks like. The update cadence and pricing are useful, but too much essential context 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?

The input schema is opaque, with generic `args` and `extra` objects and 0% schema description coverage. The description adds domain knowledge by listing currency codes and mentioning ISO codes, but it never maps those codes to the required `args`/`extra` structure or explains what `extra` is for.

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 a concrete resource: official Central Bank of Russia exchange rates, with specific currency examples and ISO codes. It lacks an explicit verb like 'get' or 'list,' but the noun phrase is unambiguous and distinct from siblings such as moex_quote.

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 this is the tool for daily official CBR FX rates for USD, EUR, CNY, GBP, KZT, and other ISO codes. It does not explicitly state when not to use it or compare it to alternatives, despite moex_quote being a plausible sibling for market data.

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, and it delivers useful operational detail: $0.05 USDC per call, ~40K input token limit, and 4096 output token cap. It stops short of mentioning auth prerequisites or error behavior, but the disclosed cost and limits are genuinely valuable.

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 compact, starts with the model name, and packs cost and token limits into a short sentence without fluff. There is no redundant structure or unnecessary elaboration.

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 tool with no annotations and an empty schema, the description must explain how to invoke it correctly. It covers the high-level behavior but omits the crucial mapping of the two required nested parameters and gives no response-format details beyond 'model response'.

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 contains only opaque args and extra objects with additionalProperties true and 0% description coverage. The description does not explain which field carries the prompt, what extra is for, or how model parameters should be passed. It adds no meaningful parameter-level 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?

Description explicitly identifies this as an LLM chat tool for Anthropic Claude Opus 5, with a clear prompt->response flow and the AnyModel provider. It also distinguishes itself from the GPT-based sibling chat tool by naming the exact model family.

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 usage for sending prompts to Claude, but gives no direct guidance on when to prefer this tool over gpt_5_6_sol_chat or any other sibling. There are no exclusions or alternative-rounting hints.

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?

It does disclose that this is a paid one-payment bundle ($0.05 USDC) and enumerates the data sources included, which is useful with no annotations present. However, the description still does not say what happens when the tool is invoked, whether payment is automatic, what input identifies the counterparty, or what the response looks like.

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 the cost is front-loaded at the end, but is not wasteful overall. The clause '3 сервіса в одном' is redundant with the enumerated services and the marketing phrasing adds no operational content, limiting structural value.

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?

Given the vague args/extra schema, no output schema, and no annotations, an agent cannot determine required inputs, output format, or invocation side effects. The description provides only service contents and pricing, which is insufficient for correct tool use.

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 is a generic wrapper with args and extra as unconstrained object placeholders, and schema description coverage is 0%. The description never explains what these parameters should contain, such as an INN, company name, or options, so an agent has no basis for constructing a valid request.

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 a concrete deliverable: a counterparty KYB dossier that bundles EGRUL, self-emloyed status (NPD), and a deep RuNet dossier. This makes the general purpose clear and differentiates it from single-purpose siblings like inn_lookup, though the wording is a marketing noun phrase rather than an explicit verb like 'get' or 'generate'.

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 guidance is given on when to select this tool instead of alternatives such as inn_lookup, ru_research, or ru_research_deep. The phrase '3 сервіса в одном' hints at a bundled use case, but there are no explicit conditions, prerequisites, or exclusions.

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 of disclosing behavior. It discloses the cost ($0.02 USDC), approximate input limit (~40K tokens), and output limit (4096), which is useful. But it does not disclose the model's temperature, tool-calling capability, latency, or that it routes through AnyModel, nor does it explain what happens on errors or token overflows. The behavioral details are thin for a mutation-like model invocation.

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 model identity and purpose, and the cost/token details are compact. However, it wastes space on 'Промпт -> ответ модели', which repeats what chat means, and omits the essential parameter usage information that would justify more length.

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, no annotations, and only two generic nested objects as parameters, the description must explain the request format and expected behavior. It gives a one-line invocation model but leaves the agent without enough information to construct a correct call, interpret the response, or choose among sibling chat/research tools.

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 two opaque parameters, args and extra, both additionalProperties: true, with 0% schema description coverage. The description does not explain what goes into args or extra, or whether the prompt goes into args.prompt or elsewhere. This is a severe gap: the agent cannot know how to structure the call.

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 mentions that it's an LLM chat powered by OpenAI GPT-5.6 Sol and that it takes a prompt and returns a model response, which goes slightly beyond a pure tautology. However, 'LLM-чат' nearly restates the tool name, and the core function (chat/completion) is implied rather than precisely defined. It does not differentiate this from the sibling claude_opus_5_chat except by model name, which the title/name already conveys.

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 provides no guidance about when to use this tool versus alternatives, such as claude_opus_5_chat or the research/search tools. Pricing and token limits are mentioned but are not usage guidance. No exclusions, preconditions, or selection criteria are 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 present, so the description carries full responsibility. It mentions cost but does not disclose what information is returned, whether it is read-only, or potential errors/side effects beyond the fee.

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 extremely concise, providing essential information (function, source, cost) without filler. It is well-structured for quick comprehension.

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?

Despite its clarity on purpose, the description lacks critical details about parameter structure, expected output, error handling, and interaction with sibling tools. The generic schema adds no information, leaving the tool under-specified for practical use.

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 defines only 'args' and 'extra' as generic objects with additionalProperties, and the description provides no details about required parameters (e.g., INN format). The schema itself has no descriptions or constraints.

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 clearly states the tool checks Russian legal entities by INN using EGRUL, and mentions the cost. This is specific and distinguishes it from likely search-oriented sibling tools.

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 usage is implied ('check by INN') but not explicit about when to prefer this over alternatives like ru_search or ru_page. No mention of prerequisites or exclusions.

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 present, so the description carries the transparency burden. It does disclose that the tool returns the last price, covers specific instruments, uses MOEX ISS, and costs $0.008 USDC. However, it does not mention delays, response shape, pagination, or any operational limitations beyond these basics.

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 compact and front-loaded with the core purpose, followed by concrete examples and pricing. It is appropriately sized with no filler, though the dense parenthetical list could be slightly better structured for readability.

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?

Given the generic schema, no output schema, and no annotations, the description leaves critical gaps: how to form a request, what the response looks like, and how symbols map to asset classes. It is adequate as a high-level summary but not complete enough for an agent to call the tool correctly without further inference.

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 is a generic wrapper with args and extra objects and 0% description coverage, so the description must explain parameters. It provides example tickers and asset types, which hints at possible values, but it does not specify the actual parameter keys, formats, or how to select a currency pair versus an index. This is insufficient for reliable invocation.

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 clearly identifies the tool as providing Moscow Exchange (MOEX ISS) quotes, listing specific asset classes: stocks, currency pairs, and indices. It includes concrete examples (SBER, GAZP, USD/EUR/CNY, IMOEX) that help disambiguate from siblings like cbr_rates, though it lacks an explicit verb such as 'get' or 'fetch'.

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 guidance on when to use this tool versus alternatives such as cbr_rates or ru_search. The description implies usage for MOEX quotes but does not state exclusions, fallback conditions, or how it relates to sibling tools.

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 states the action and the cost but does nota disclose input requirements, invalid-address handling, whether it is a paid external call with rate limits, or what exactly is returned. 'Normalization' hints at the operation but leaves the behavioral contract highly underspecified.

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 a single, focused sentence that communicates the domain, the operation, the relevant fields, and the cost. There is no redundant wording, and the key 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?

Given that the schema is generic, there is no output schema, and no annotations exist, this description is inadequate for correct invocation. Missing pieces include the exact input format, the normalized output shape, examples, error behavior, and selection criteria among sibling postal tools. The stated cost and field list provide only minimal context.

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 only generic 'args' and 'extra' objects, and description coverage is 0%. The description lists fields such as index, region, street, and house, which helps slightly, but it does not say whether these are input fields, output fields, or both, nor how they map to args. An agent cannot reliably build a correct request payload.

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 clearly says the tool normalizes a Russian address and lists the relevant components: index, region, street, house. That is a specific verb-plus-resource statement, and it is distinguishable from siblings like pochta_track, pochta_tariff, and pochta_offices. It does not fully explain what normalization produces or what input it expects, so it stops short of 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 guidance about when to use this tool versus related siblings such as pochta_zip or pochta_offices. The only hint is the word 'normalization,' so when-to-use context is implied but no alternatives or exclusions are mentioned.

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?

Since no annotations are provided, the description carries the full transparency burden. It usefully discloses a $0.04 USDC payment and a one-payment bundle structure. However, it does not state whether the operation is read-only, whether all five services are actually invoked, or what other side effects or prerequisites exist.

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 compact and front-loads the bundle name and contents; the price is essential information. It loses one point because the marketing-style phrasing is not an invocation specification, but no words are wasted.

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 tool with an opaque two-object schema, no output schema, and no annotations, this description is far too incomplete. It does not explain what goes into args/extra, what the response contains, or what preconditions apply, making correct invocation impossible.

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 description coverage and exposes only opaque args/extra objects. The description never maps 'адрес, индекс, отделение, стоимость, срок' to specific parameters or explains how to structure the request. An agent has no way to know what values to supply.

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 'Доставка Почты России' bundle and lists five covered services (address, index, office, cost, delivery time), so it is more than a tautology. However, it lacks an action verb: it does not say whether the tool returns data, purchases a bundle, or executes several service calls. The actual operation remains ambiguous.

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 phrase '5 сервисов в одном' implies this tool is the combined option when multiple delivery-data services are needed, and the price distinguishes it from the individual sibling tools. There are no explicit when-to-use or when-not-to-use instructions and no named alternatives, so the agent must 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?

Since no annotations are provided, the description must carry the behavioral burden. It does reveal the output unit (days) and a flat cost ($0.01 USDC), but it does not mention any side effects, required permissions, behavior on invalid or nonexistent indices, rate limits, or whether the operation is read-only. The cost disclosure is helpful but leaves major 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?

The full content is a single line with no filler: the core function, the output unit, and the cost. It is succinct and front-loaded, maximizing clarity per word.

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 tool with generic input schema, no output schema, and no parameter documentation, the description omits critical context: the exact structure and types of the postal indices, the response format beyond a count in days, and behavior for invalid inputs. An agent cannot confidently determine the correct call or interpret the result.

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 offers only generic 'args' and 'extra' objects with no property descriptions (0% coverage). The description hints that the tool needs two postal indices, but it does not explain how those indices should be structured within 'args' or whether 'extra' is required. The agent cannot reliably know how to construct the request.

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 clearly identifies the function: delivery times between postal indices in days, and scopes it to Russian Post (Почта России). This distinguishes it from sibling tools like pochta_tariff (pricing) and pochta_track (tracking), though it lacks an explicit verb like 'calculates' or 'estimates'.

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 guidance is given about when to choose this tool over alternatives such as pochta_tariff or pochta_offices. The description states only what the tool returns, not in which scenario a caller should invoke it, nor any conditions or prerequisites like requiring two indexes.

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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It does state the cost involved (0.01 USDC) and the lookup-only purpose, which are useful context. However, it says nothing about request limits, error behavior, authentication, response structure, or whether the lookup respects privacy constraints.

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 a single, front-loaded sentence with no filler. It conveys the resource, the query modes, and the cost of the call in a compact way. Every token contributes something useful.

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 external API with no output schema and a generic args structure, the description does not provide enough to reliably invoke the tool. It omits the concrete field names, valid value formats, response shape, and necessary guardrails in case of invalid coordinates or unknown postal codes. It is a useful summary but not a complete specification.

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 is a generic wrapper with additionalProperties:true and no property descriptions, providing virtually no parameter meaning. The description adds some meaning by mentioning 'by index' and 'by coordinates', but it still does not say the argument names, exact formats, or how to structure the 'args' object. With schema coverage at 0%, the description only partially compensates.

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 clearly identifies the resource ('Почта России' post offices) and the two main modes of operation (by postal code or by coordinates). This is enough to distinguish it from most sibling tools such as tariff or tracking. However, it uses a noun phrase rather than an explicit verb like 'search' or 'return', so it is clear but not perfectly action-oriented.

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 the use cases: when an agent needs post offices by postal code or nearest to coordinates. Yet it does not explicitly say when to choose this tool over the sibling tools, and it gives no exclusions or fallback guidance. The usage 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?

There are no annotations, so the description must carry the burden. It does convey that this is an official-API, read-style tariff lookup and even discloses the monetary cost. It still doesn't clarify whether authentication is needed, what format the response takes, or whether any side effects exist. A small gap, but not a major hide of 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?

The description is one line and immediately specifies the domain ('Post Russia'), the purpose ('cost and delivery time'), the scope ('between inde'), and even cardinality. Every sentence 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?

The tool has no. output schema, no parameter descriptions, and no annotations. The description only provides the semantic purpose. An agent would not know how to map a source/destination pair into the wrapper schema, nor what to expect in the response. This is slightly too sparse to be considered 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?

The schema offers no descriptive coverage (0%) and the description only implies 'between indices' — meaning the tool needs at least two postal indexes. It does not specify how to pass them under the required 'args' object, or explain 'extra'. The agent cannot reliably determine parameter names or value formats from the description 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 clearly states the tool's purpose: providing Russian Post shipping costs and delivery times between postal indices, using the official API. The $0.01 USDC pricing also tells the agent this is a paid, likely fast operation. This distinguishes it from siblings like pochta_track or pochta_address.

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 gives a clear-use context: 'cost and delivery time between indices.' However, it does not mention when not to use it or compare it with related siblings such as pochta_delivery_time, which appears to handle delivery times alone. The intended usage is implied but not explicitly differentiated.

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 describes the operation at a high level but does not disclose whether the tool is read-only, what constitutes a successful response, how errors/manifestations are handled, or any other behavioral traits. The description adds no transparency beyond the action itself.

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 one short front-loaded sentence plus a price indication. It contains no fluff and gets directly to the purpose. However, its conciseness borders on under-specification, so it does not earn a 5.

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?

Given the lack of output schema, annotations, and meaningful parameter documentation, the description is incomplete for actual tool invocation. An agent would not know exactly what to place in the generic 'args' object or what response shape to expect. The description serves as a label but not as a complete spec.

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 is a generic wrapper with 'args' and 'extra' objects, and schema description coverage is 0%. The description does imply that a track number is needed, but it never explains how to pass it into 'args', what key name to use, or what other values are expected. This is not sufficient for an agent to construct a correct call.

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 a specific action ('отслеживание' / tracking), a specific resource ('отправления' / shipments), and the required key ('по трек-номеру'). This clearly differentiates it from sibling Rospochta tools like pochta_address, pochta_tariff, and pochta_delivery_time, which handle different services.

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 phrase 'по трек-номеру' implies this tool is used when a Russian Post tracking number is available, but the description gives no explicit when-to-use or when-not-to-use guidance, and does not contrast with alternative pochta_* siblings. Usage is implied rather than instructed.

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?

There are no annotations, so the description carries the full burden. It does usefully disclose that this is a paid lookup ($0.01 USDC) and implies a read-only address retrieval operation, but it does not explain response format, live API behavior, authentication needs, errors, or rate limits.

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 extremely concise and front-loaded: the core behavior is stated in the first sentence, and the price in the second sentence. Every token earns its place and the structure wastes no space.

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, no annotations, and an open-ended args schema, the description leaves too much unsaid. It is too thin to fully equip an agent to construct a correct call or distinguish it from the related Russian Post tools beyond the zip-code hint.

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%, and the schema is a generic args/extra wrapper with additionalProperties, providing no meaningful parameter documentation. The description's phrase 'по индексу' indicates that a postal code is the key concept, but it never identifies expected keys, types, or which values go into 'args' versus 'extra'.

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 ('Почта России'), a specific output ('адрес отделения и населённый пункт'), and the lookup key ('по индексу'). It is clearly distinguishably a postal-code lookup at the description level, though it does not explicitly contrast itself with sibling tools.

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 usage guidance is provided beyond the bare lookup scenario. The description never says when to prefer this over pochta_address, pochta_track, or pochta_offices, nor does it give prerequisites, exclusions, or alternative selection criteria.

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?

There is no disclosure of side effects, permissions, error handling, or outcomes beyond the conversion. The cost is mentioned but no other behavioral aspects are addressed, and annotations are absent.

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 brief and to the point, which is concise. However, it is not well-structured; it uses an arrow notation and includes pricing but omits essential usage details, so it balances brevity with incompleteness.

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?

The tool lacks context about how it fits with sibling tools (inn_lookup, ru_search). No explanation of input requirements, output format, or differences from alternatives, leaving the tool's role ambiguous.

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 parameters 'args' and 'extra' are generic objects with no description of expected contents. The description does not explain what fields are needed (e.g., URL, options), making it impossible to invoke correctly 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 clearly indicates the tool converts a Russian page URL to LLM-ready Markdown, and notes the cost. The arrow mapping and cost info make the purpose reasonably clear, though it could be phrased more explicitly as a verb phrase.

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 guidance is provided on when to use this tool versus alternatives like inn_lookup or ru_search. The description lacks any context about typical use cases or 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?

With no annotations provided, the description carries the full burden. It discloses the payment cost ($0.02 USDC) and the outputs (Markdown top pages), but does not clarify side effects, authentication needs, failure handling, or whether the operation is read-only. This is minimal but not misleading.

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 a single sentence, very concise, and front-loaded with the key value proposition (Cyrillic search + top pages in Markdown) and cost. It earns its place, though it is perhaps too terse and omits essential usage details.

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?

Given the generic schema, no output schema, and lack of parameter docs, the description is insufficient for an agent to correctly invoke the tool. It provides a high-level idea but omits how to structure inputs and what to expect in return, making it incomplete for a 2-parameter 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?

The schema has generic 'args' and 'extra' objects with no property definitions and 0% description coverage. The description does not explain what arguments are expected, such as search term, number of pages, or output format details. It fails to compensate for the complete lack of schema documentation.

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 tool provides a research package combining Cyrillic search and top pages in Markdown format, with a clear payment amount. It is specific about the resources and actions, but does not explicitly differentiate from sibling tools like ru_search or ru_page beyond implying a bundled operation.

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 guidance is given on when to use this tool versus its siblings. It does not mention scenarios, exclusions, or alternatives. The phrase 'with one payment' hints at a batch use case, but there is no explicit 'use this when...' or 'do not use for single lookups' type of guidance.

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 full burden. It does not disclose any behavioral traits such as payment processing ($0.05 USDC is mentioned but not explained), whether it is a read-only operation, what counts as a 'search', how pagination/limits are handled, or potential side effects like billing. The description is largely a pricing/package statement with no behavioral transparency.

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 very short (one line), which is concise, but it is not well-structured: it jumps between Russian and English, and the key information (purpose, usage, parameters) is missing. It earns credit for brevity but fails to provide necessary substance.

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?

The tool has a complex research package (3 searches, up to 10 pages, payment), but the description only states the package contents and price. It lacks any details about inputs, expected output format beyond 'Markdown', execution flow, or error handling. With no annotations and no output schema, the description is severely incomplete for an agent to use this tool 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?

The input schema has 2 parameters ('args' and 'extra') with 0% schema description coverage. The description does not explain what 'args' or 'extra' contain, what fields are expected, or how they map to the research package. The description adds no meaningful parameter semantics beyond the schema's generic names.

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 'Research-пакет deep: 3 поиска + до 10 страниц в Markdown одним платежом. $0.05 USDC' mixes Russian and English, and focuses on package pricing and outputs (3 searches, up to 10 pages in Markdown) without a clear verb+resource statement. It does not clearly differentiate from sibling tools like 'ru_research' (likely a lighter version) or 'ru_search', and the title is null.

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 usage for deep research (package of 3 searches + up to 10 pages), but does not specify when to choose this over 'ru_research' (standard), 'ru_search', or 'inn_lookup'. No exclusions or alternative guidance are 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?

Annotations are absent, so the description carries full responsibility for behavioral disclosure. It mentions a cost ($0.02 USDC), which is a useful trait, but does not explain side effects, return format, or read-only nature. This is minimal transparency for a tool that likely performs a network operation.

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 a single short sentence (in Russian) with no fluff. It conveys the core purpose succinctly, but the brevity sacrifices essential details, which is handled under completeness. As conciseness alone, it is efficient.

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?

Given the generic schema, lack of annotations, and no output schema, the description is severely insufficient. It fails to explain how to invoke the search, what parameters to provide, expected results, or any operational constraints. The complexity of the underlying tool is not reflected in the description.

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 0% – the input schema only defines wrapper objects with additionalProperties, providing no meaningful parameter definitions. The description adds no parameter information, so agents have no idea what to pass. This is a critical 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 states the tool performs a web search specifically for Cyrillic content, which is a clear verb+resource. However, it does not explicitly contrast with sibling tools (inn_lookup, ru_page), so it lacks clear differentiation, though the purpose is understandable.

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 provides no guidance on when to use this tool versus alternatives. It merely states it is a Cyrillic web search, without indicating prerequisites, exclusions, or when a sibling would be more appropriate.

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