Server Quality Checklist

Tool Scores

• searchA
  4.1/5.0
  Behavior3/5

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

  Without annotations, the description carries the full burden. It implies the tool is read-only through its search nature, but does not explicitly state that no modifications occur or disclose any other behavioral traits. The return format is provided, which adds some transparency.

  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 concise and well-structured, with a brief intro, a clear Args list, and a return format. Every sentence adds value without 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 in the description, it is mostly complete. It lacks mention of error handling or pagination, but the limit parameter covers result count. A minor gap in completeness.

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

  Parameters5/5

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

  The description fully documents each parameter, adding meaning beyond the schema: query is a keyword/partial match, level lists exact CEFR values, and limit specifies range and default. This compensates for the 0% schema coverage.

  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 searches the 29k EN→UA sense index and returns matching entries with specific fields. It distinguishes itself from siblings (check, check_natural, render, substantiate) by focusing on search rather than validation or rendering.

  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 provides contextual hints ('useful for vocabulary lookups') but does not explicitly state when to use this tool versus alternatives or when not to use it. No exclusions or comparisons are made with sibling tools.

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

• substantiateA
  4.1/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries full burden. It discloses that the tool returns independent attestations from several primary sources and details the output structure. However, it lacks explicit statements about side effects (e.g., read-only nature), authentication requirements, or rate limits. The behavior is adequately described but could be more transparent.

  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 well-structured with a clear purpose statement, a bulleted usage section, and formal Args/Returns sections. It is concise, front-loaded, and every sentence adds value. No extraneous text.

  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 output schema is richly defined in the description, and the tool has only two parameters, the description covers purpose, usage, parameters, and output comprehensively. It does not mention error handling or edge cases like unrecognized phrases, but the confidence field mitigates this. Overall very complete.

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

  Parameters5/5

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

  The input schema has 0% description coverage, but the description fully compensates by explaining 'phrase' (any Ukrainian phrase) and 'sources' (optional comma-separated source IDs, default all). This adds meaning beyond the schema, making it clear how to use each parameter.

  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 'Get the citation chain for a Ukrainian phrase', which is a specific verb+resource. It lists the sources involved, making the purpose immediately understandable. However, it does not explicitly differentiate from sibling tools like check, search, or render, though the uniqueness is implied.

  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 includes a bullet list under 'Use this when:' with three explicit use cases (backing up claims, explaining correctness, finding historical attestations). This provides clear guidance on when to invoke the tool, but it does not include when not to use it or mention alternative tools.

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

• checkA
  4.6/5.0
  Behavior4/5

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

  Describes the internal engines, return type with position-indexed issues, severity, suggestions, and character limit. No annotations provided, so description carries full burden; it is transparent but lacks details like rate limits or error handling.

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

  Conciseness4/5

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

  The description is well-structured and front-loaded with the main purpose, then details engines, guidelines, and return format. It is fairly concise, though a bit verbose with engine details.

  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 single parameter and the detailed return type in the description (no formal output schema but a JSON example), the description is sufficient for an agent to understand and invoke the tool. Lacks some edge cases but overall complete.

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

  Parameters5/5

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

  The input schema only defines 'text' as a string; the description adds crucial context: 'Ukrainian text (up to ~5000 chars)', which goes beyond schema and clarifies constraints.

  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 it performs a 'Full Ukrainian grammar + spelling + surzhyk check' and lists the engines used. It distinguishes itself from sibling 'check_natural' by specifying it validates comprehensively, not just naturalness.

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

  Usage Guidelines5/5

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

  Explicitly says to use when user asks 'is my Ukrainian correct?' or wants comprehensive validation, and contrasts with 'not just naturalness', providing clear guidance vs. alternatives.

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

• check_naturalA
  4.8/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. It explains return format with verdicts and their meanings (calque-prone vs natural), sources, and fields. However, it does not explicitly state it is read-only or non-destructive, though implied by analysis nature.

  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?

  Well-structured with clear purpose, usage instruction, and structured return format using bullet points. No superfluous sentences; each sentence adds value.

  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?

  With output schema described in detail and one input parameter fully explained, the description is complete for the tool's complexity. Sibling tools are not compared, but usage guidance is sufficient.

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

  Parameters5/5

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

  Schema has zero description coverage; description adds 'Ukrainian text (2 chars min)' which specifies language constraint and minimum length, adding significant meaning beyond type string.

  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?

  Clearly states the tool checks Ukrainian text for calque-prone phrases and naturalness, with specific verb 'Check' and resource 'Ukrainian text'. Distinct from siblings like 'check' which is more general, and 'render', 'search', 'substantiate' which serve different purposes.

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

  Usage Guidelines5/5

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

  Explicitly says 'Use this AFTER drafting Ukrainian text, BEFORE returning it to the user' and instructs to rewrite calque-prone spans before delivery. This provides clear when-to-use and action guidance.

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

• renderA
  4.8/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries full burden. It discloses that renderings come from multiple sources, handles polysemy by returning per-sense results, and includes the full output schema. No behavioral contradictions.

  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 well-structured with a clear purpose, usage context, source attribution, and output format. Every section adds value without redundancy.

  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?

  Given the presence of an output schema (described in detail), the description covers all necessary context: input parameters, output structure, data sources, and when to use. Nothing is missing for effective tool selection and invocation.

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

  Parameters5/5

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

  Schema coverage is 0% (no parameter descriptions in schema), but the description includes an 'Args' section explaining 'en' (English word) and 'sense' (optional filter). This adds full meaning beyond the schema property titles.

  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's purpose: 'Get authentic Ukrainian renderings for an English word or sense.' It uses a specific verb ('Get') and resource ('Ukrainian renderings'), and the context of translation/vocabulary tasks distinguishes it from sibling tools like search or substantiate.

  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 provides explicit when-to-use guidance: 'Use this for translation or vocabulary tasks where you want idiomatic Ukrainian (not a calque or AI-guessed translation).' It does not explicitly list when not to use or compare to siblings, but the context is clear.

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