Server Quality Checklist

Tool Scores

• check_compliance_38fzB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description carries full burden. It states the tool is deterministic and free, but does not disclose important behavioral traits such as whether it modifies any state, requires specific permissions, or has side effects. The output is a verdict, which is clear, but other behaviors are hidden.

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

  Conciseness4/5

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

  The description is a single concise sentence that conveys the core function and output. There is no wasted text. However, it could be slightly expanded to include prerequisite information without becoming verbose.

  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?

  While the schema and output schema cover parameters and return values, the description lacks context on prerequisites (e.g., requiring results from sibling audit tools) and how the collected features relate to the input. For a tool in a compliance domain, this gap could hinder correct usage.

  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?

  Schema coverage is 100% with each parameter having a description. The tool's description does not add meaning beyond what the schema already provides (e.g., 'url' as context, 'erid' as token). The baseline of 3 applies because the schema already documents parameters adequately.

  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 clearly states that the tool performs a deterministic compliance check against 38-FZ, outputting a verdict of 'ok', 'issues', or 'insufficient_data'. It distinguishes from sibling tools like 'audit_ad_page' (which audits a page) and 'verify_erid' (which validates an ERID token) by focusing on compliance verification based on collected features.

  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?

  No explicit guidance on when to use this tool versus alternatives is provided. The description implies it should be used after collecting features (possibly from other audit tools), but this is not stated. No exclusions or alternative tool recommendations are given.

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

• audit_batchA
  3.7/5.0
  Behavior3/5

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

  No annotations provided. Description mentions tariff requirement (Pro, MCP_ERID_API_KEY) which is helpful, but does not disclose other behavioral traits like error handling, rate limits, or nature of output beyond 'table of results'.

  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?

  Single sentence with no waste. Key information (batch, table of results, tariff requirement) is front-loaded and presented efficiently.

  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?

  Given the simple single-parameter input and existence of an output schema (not described), the description covers the basic purpose and tariff context but lacks details on result interpretation or expected output format.

  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?

  Schema description coverage is 100%; the description adds no additional meaning beyond what the schema already provides (list of placement URLs). It repeats the parameter purpose without extra context.

  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?

  Description clearly states 'batch verification of placements' and 'table of results for each URL', which distinguishes it from sibling tools like audit_ad_page that handle single URLs. The tariff requirement adds context.

  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 implies use for batch verification but does not explicitly state when to use this tool vs alternatives (e.g., audit_ad_page for single URLs) or any exclusions.

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

• audit_ad_pageA
  4/5.0
  Behavior3/5

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

  No annotations provided, so description carries burden. It discloses what is checked (label, advertiser data, erid) and that it's free, but omits details on error handling, authentication needs, 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.

  Conciseness5/5

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

  Two concise sentences that front-load the purpose and include a key trait (free). No unnecessary words.

  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 tool's simplicity (one param, output schema exists), the description covers the core functionality. Lacks mention of prerequisites or error states, but sufficient for basic understanding.

  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% with a single parameter. Description adds context by specifying the URL is for an ad page/post, supplementing the schema's minLength constraint.

  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 clearly states the tool audits an ad page, checking for specific elements: 'Реклама' label, advertiser data, erid presence. It distinguishes from sibling tools like audit_batch and verify_erid by focusing on a single page audit.

  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?

  Usage context is implied (audit a single ad page), but no explicit guidance on when to use this versus sibling tools (e.g., audit_batch for batch processing) or conditions like URL validity.

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

• explain_marking_requirementA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It states 'Free' and indicates it's a reference tool, implying no side effects, but does not explicitly disclose behavioral traits like read-only, auth needs, or rate limits. The term 'Справка' (reference) suggests non-destructive behavior, but transparency is adequate but not thorough.

  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 concise sentence plus the word 'Free' ('Бесплатно'), front-loaded with the tool's purpose. Every word adds value, with no redundancy or filler. It is efficiently structured.

  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 simple structure (one parameter, output schema present), the description is largely complete. It explains the tool's function adequately without needing to detail output since output schema exists. Minor room for improvement in listing exact topics, but the parameter description already covers them.

  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?

  Schema description coverage is 100%, so the input schema already documents the 'topic' parameter with examples (erid, ord, etc.). The tool description adds no extra meaning beyond the parameter description. Baseline of 3 is appropriate; the description does not enhance parameter understanding.

  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 ('Reference on advertising marking requirements...') clearly states the tool explains advertising marking requirements, including key concepts (erid/ORD/ERIR), responsibilities, deadlines, and fines. It distinguishes from sibling tools (audit, verification) by being explanatory rather than auditing.

  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 description implies usage context: use this tool for explanations on marking requirements. The sibling tool names (audit, check compliance, verify) contrast with this explanatory tool, so context for when to use is clear. However, it lacks explicit when-not-to-use or alternative guidance.

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

• verify_eridA
  4.4/5.0
  Behavior4/5

  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 details the validation steps (format, control signs, public data, readability) and notes the tool is free. This covers key behavioral aspects for a simple validation tool.

  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 sentence, concise and front-loaded with the main purpose. Every part adds value with no redundancy.

  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 tool's simplicity and the presence of an output schema (not shown), the description adequately covers what the tool does. It mentions the key validation aspects without over-explaining.

  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% (one parameter). The description adds an example value ('2Vfnxxxxxx'), which adds clarity beyond the schema's formal definition.

  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 clearly states that the tool validates an erid token, checking format, control signs, public data presence, and readability. This is specific and distinct from sibling tools which focus on auditing or compliance.

  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 description implies usage for validating erid tokens, with its purpose well-separated from siblings. However, it does not explicitly state when not to use or provide alternative suggestions.

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