Server Quality Checklist

Tool Scores

• direct_callA
  3.9/5.0
  Behavior2/5

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

  With no annotations, the description must carry the behavioral burden, but it only states the HTTP mechanics and broad scope. It does not warn that this universal call can mutate or destroy production data (delete, archive, suspend are possible), nor mention sandboxing, auth needs, or side effects. 'Покрывает всё управление' hints at writes but does not disclose consequences.

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

  Conciseness5/5

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

  Three dense sentences with no filler. The first sentence front-loads the core call pattern, the second scopes what it covers, and the third gives a direct pointer to the reference tool. Every sentence earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description is serviceable for a generic wrapper: it names the endpoint shape, scope, and prerequisite reference. But with no annotations or output schema, it omits auth context, sandbox behavior, and any statement about the raw response shape; those are left to schema fields, which is a noticeable gap for a tool that can perform destructive operations.

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

  Parameters4/5

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

  Schema coverage is 100%, so the baseline is 3. The description adds real semantic value by showing how parameters map to the request structure: service goes into the URL path and method/params form the JSON body. It also tells the agent where to find valid service/method names, though sandbox and client_login are left to the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description is explicit: 'Универсальный вызов Яндекс Директ API v5' followed by the exact HTTP action 'POST на /json/v5/{service} с телом {method, params}'. It lists the covered resource domains (campaigns, adgroups, ads, keywords, bids, retargeting, dictionaries), which clarifies scope and distinguishes it from the more specialized sibling tools.

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

  Usage Guidelines4/5

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

  The phrase 'Сначала загляни в direct_reference за именами сервисов, методов и формой params' gives a concrete prerequisite and points to an alternative tool. It clearly establishes direct_call as the universal management entry point, though it does not explicitly state when to prefer direct_status or direct_report.

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

• direct_reportA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden and discloses important behavior: it waits for report readiness, handles 201/202 retry codes, and returns TSV. It stops short of describing authentication, error conditions, or whether report generation has side effects or costs, but the main operational surprise is well covered.

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

  Conciseness5/5

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

  The description is a single dense sentence that front-loads the service and key behavior. It avoids repeating schema details and contains no filler, making it appropriately sized and easy to scan.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the rich schema coverage and the absence of an output schema, the description covers the non-obvious long-running behavior and the output format. It is mostly complete for invocation purposes, with minor gaps around error handling and explicit sibling-tool relationships.

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

  Parameters3/5

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

  The input schema already provides full descriptions for all parameters, including the nested ReportDefinition fields and defaults. The description adds only the high-level 'ReportDefinition' concept and TSV return format, which the schema already covers, so it contributes little beyond the structured definitions.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states the resource ('Reports API v5') and clarifies the operation: it accepts a ReportDefinition, waits for report readiness, and returns TSV. It is clear enough to identify the tool as a report/statistics retrieval tool, though it lacks an explicit action verb and does not directly contrast 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.

  Usage Guidelines4/5

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

  The opening phrase 'Статистика через сервис Reports API v5' provides clear context for when to use the tool: to obtain statistics via Reports API v5. It states the self-waiting behavior, distinguishing it from a manual status-checking tool, but it does not explicitly list alternatives or exclusions.

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

• direct_statusA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It is transparent that the tool runs a probe API call ('пробный clients.get'), checks the token/environment/points, and explicitly states that the token is not disclosed. This covers the key behavioral facts an agent needs to know.

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

  Conciseness5/5

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

  A single Russian sentence front-loads the purpose and then provides a compact enumeration of checks. Every clause carries information, with no filler or repetition.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a zero-parameter status tool with no output schema, the description gives enough context to call it correctly: it defines what is tested and what is not exposed. It does not spell out the exact return format, but this is not critical given the enumerated status categories.

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

  Parameters4/5

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

  The tool has zero parameters and the schema has full coverage, so there is nothing for the description to add about parameter meaning. The description's focus on connection state is consistent with requiring no input.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description names a concrete action ('Проверить подключение' – check connection) and a specific resource (Yandex Direct), and enumerates the exact diagnostics performed: token presence, environment, API availability via a trial clients.get, and remaining points. This clearly sets it apart from sibling tools like direct_call or direct_report.

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

  Usage Guidelines3/5

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

  The description makes it clear this is a diagnostic/health-check tool by framing the action as checking connection and listing status checks. However, it does not explicitly say 'use this when verifying setup before direct_call' or name alternatives/exclusions, so the 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.

• direct_referenceA
  4.5/5.0
  Behavior4/5

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

  There are no annotations, so the description carries the burden of behavioral disclosure. It does this well by listing the informational content and framing the tool as a read-only reference/cheat sheet. It does not explicitly state that it has no side effects or describe the return format, but the reference framing makes the behavior sufficiently clear.

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

  Conciseness5/5

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

  Two sentences with no wasted words: the first front-loads what the tool provides, and the second gives the actionable trigger. Every phrase earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a zero-parameter reference tool, this is complete: it specifies the domain (API v5), the exact reference content, and when to call it. The lack of an output schema is mitigated by the explicit enumeration of what the cheat sheet covers.

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

  Parameters4/5

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

  The input schema is empty with zero parameters, so the baseline is 4. The description does not discuss this tool's parameters, but it uses the word 'params' only in the context of examples for direct_call, avoiding confusion. No additional parameter explanation is needed.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description identifies the tool as a 'cheat sheet' for API v5 and enumerates its contents: services, methods, params examples, report types, rate units, and limits. This clearly distinguishes it from sibling execution tools like direct_call and direct_report, so an agent knows exactly what this reference operation is for.

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

  Usage Guidelines4/5

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

  It gives an explicit when-to-use instruction: call this before the first direct_call to avoid guessing fields. This is clear context, but it does not mention when not to use it or contrast it with direct_status/direct_report, so it stops short of a full 5.

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