mcp-everything: Russian APIs

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds useful behavior beyond that: the output is large, and coverage explicitly separates what is documented here from what must be checked in official documentation. It does not describe the return shape in detail, but the listed sections give a reasonable preview.

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 front-loaded with the core purpose, then lists the document contents compactly, and ends with the alternative-tool warning. Every phrase carries useful information; 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?

For a single-document retrieval tool with a simple one-parameter schema and annotations covering safety, the description supplies the missing context: what the document contains, that it is large, and when to prefer a narrower sibling. No output schema exists, but the enumerated sections adequately describe the return.

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?

There is only one parameter, slug, and schema description coverage is 100% with an example (yookassa). The description adds no parameter-specific semantics beyond what the schema already provides, 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 precisely what the tool returns: the entire service record as one document, and enumerates its sections (coverage, scenarios, authorization, methods, errors, nuances). It also explicitly distinguishes itself from the sibling get_scenario, so an agent can choose correctly 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?

It gives an explicit when-not-to-use rule: if the task is already clear, use get_scenario instead. The warning that the response is voluminous adds practical guidance about cost, and the full-record use case is implied clearly enough for 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 readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds value beyond them by enumerating exactly what the response contains (params, examples, auth, base URL, doc link), which helps an agent judge whether it needs this tool. Missing only failure behavior (e.g., unknown slug/method).

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

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

Two compact sentences, with the inventory of returned content front-loaded and the cost/benefit note (saves context) placed last. 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?

There is no output schema, and the description compensates by listing the returned items, which is exactly what an agent needs to decide to call it. Only edge-case behavior (method not found) is unaddressed, a minor gap for a simple two-parameter read.

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% and both parameters are documented with examples ("yookassa", "POST /payments"), so the schema does the heavy lifting. The description adds no additional meaning about the slug or method format, making the 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?

The description states what a caller gets for one API method: parameters, request/response examples, auth, base URL, and a docs URL. The verb is implicit ("Один метод") rather than explicit, and it does not directly contrast with siblings like get_integration or get_scenario, but the scope (single API method for a service slug) 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?

"Экономит контекст, если нужен только он" gives a clear use condition: fetch a single method when that is all that is needed, implicitly contrasting with browsing a broader catalog. It lacks an explicit negative case (e.g., use list_catalog to discover methods), so it falls 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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by disclosing the scope of returned content and the caveat that it is usually sufficient for writing an integration.

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 sentences, front-loaded with what the tool returns, followed by sufficiency guidance and parameter sourcing. There is no redundant or filler text.

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 enumerates the returned content and explains where to get the required scenario id. It is nearly complete for a read-only retrieval tool, though sibling differentiation could be stronger.

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 both slug and scenario are already documented with examples. The description adds value by explaining that the scenario id should be obtained from search or get_integration, which is not captured in the schema.

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 that this returns a task-specific integration instruction containing steps, code examples, methods, auth, base URL, pitfalls, and documentation links. It is specific about the resource and content, though it does not explicitly distinguish itself from sibling tools like get_integration or get_method.

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 says the scenario id should be taken from search or get_integration and that the result is usually enough to write an integration, which implies usage. However, it does not explicitly state when to use this tool instead of get_integration or get_method, nor does it provide 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?

Annotations already declare readOnlyHint, idempotentHint, closed-world and non-destructive, so the safety profile is covered. The description adds that results carry scenarios and are organized by industry, which is useful output-shape context, but says nothing about result size, pagination, or how the industry argument affects grouping/filtering.

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

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

Two short sentences, zero padding. The scope statement comes first and the routing guidance second, which matches how an agent reads it.

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-optional-param read-only tool with rich annotations this is close, but with no output schema the description should clarify return volume/format and how `industry` behaves. As written, an agent knows when to call it but not exactly what it will get back or whether omitting `industry` returns everything.

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

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

Schema description coverage is 0%, so the description must compensate. 'по отраслям' hints that the single optional `industry` parameter relates to industry grouping, but it's ambiguous whether it filters results or merely orders them. The enum itself enumerates valid values, but the description adds only marginal meaning.

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 and scope: all catalog services, grouped by industry, with scenarios included. An agent can distinguish it from `get_scenario`/`get_integration` by the 'all services' breadth, though the verb is implicit ('Все сервисы') rather than an explicit action.

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

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

Gives two concrete triggers: when `search` returned nothing, or when the agent needs to pick a service. It explicitly names the sibling `search` as the alternative. It doesn't mention the other siblings (get_scenario, get_integration) or state when NOT to use this, so it stops short of a full routing rule.

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, closed-world behavior, and the description adds valuable context beyond them: what is returned (scenarios with steps and code, plus methods) and that both Russian and English queries are understood. Pagination behavior is left implicit despite a page parameter, which keeps it from a 5.

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

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

The purpose and usage triggers are front-loaded in the first two sentences, which is good. However, the enumeration of 40+ catalog services followed by 'и ещё 41' is bulky and partially truncated, adding bulk without full 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?

There is no output schema, so the description carries the burden of explaining returns, and it does state that scenarios (steps + code) and methods come back. Combined with the annotation coverage, an agent has enough to search correctly, though it does not explain what an empty result or pagination looks like.

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 67% with a well-documented enum for industry and examples for query, so the schema does much of the work. The description contributes only the language-flexibility note (русский и английский), and says nothing about the page parameter or how results are ordered.

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 (Ищет) and resource (по задаче, сервису или методу среди российских API) and clarifies the return payload (готовые сценарии шаги+код и методы). This distinguishes it from siblings like get_scenario/get_method, which retrieve by identifier rather than searching.

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 a clear trigger condition (нужно интегрироваться с российским сервисом) with concrete domains: приём платежей, доставка, CRM, маркетплейсы, учёт, SMS. It does not explicitly name alternatives such as list_catalog or get_scenario as the next step, but the usage context is unambiguous.

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