Server Quality Checklist

Tool Scores

• generate_horoscopeA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and succeeds. It explicitly discloses side effects (image rendering to a temporary path, read-only/stateless), auth/rate limits (fully local, no authentication or rate limits), and error behavior (returns error dictionary). This is exceptionally transparent for a tool with no annotation support.

  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?

  Although long, the description is well-structured with clear headings (Purpose and Comparison, Side Effects, Auth/Rate Limits, Prerequisites, Parameter Guidelines, Output Schema). Every section adds necessary detail for a complex 10-parameter tool, without irrelevant fluff.

  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 no annotations, no output schema, and high complexity, the description is remarkably complete. It covers side effects, auth, prerequisites, all parameters, output structure (both image and non-image branches), and error conditions. The output schema section even details the chart_data structure, so the agent knows exactly what to expect.

  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 description coverage is 0%, but the description compensates fully. It explains every parameter's meaning, accepted formats (e.g., hour_val as '14:30', 'Ngọ', or branch index; timezone as integer or h:30 string), defaults, and interactions (e.g., timezone only affects boundary rounding of astronomical events). This greatly exceeds the schema information.

  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 opens with a specific verb+resource statement: 'Generate a full Tu Vi (Vietnamese horoscope) chart from raw birth details, with optional high-quality visual chart image rendering.' It distinguishes from siblings via the 'Purpose and Comparison' section that directs usage to compute and inspect a birth chart from scratch, which is clearly distinct from the sibling tools (get_van_han, get_auspicious_info, convert_calendar).

  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?

  Provides clear context: 'Use this tool when you want to compute and inspect an astrological birth chart from scratch for arbitrary birth details.' However, it doesn't explicitly name alternative sibling tools or state when not to use this tool, so it stops short of the explicit when/when-not/alternatives level. Prerequisites and parameter guidelines add further usage context.

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

• get_auspicious_infoA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and does so exceptionally well. It discloses timezone handling, defaults, the UTC+7 anchor for metadata lookups, and the potential slight differences near tiết-khí boundaries. It also outlines the return structure, providing transparency without needing annotations.

  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 clear headings (Purpose, Parameters, Returns) and is appropriately detailed for the tool's complexity. Every sentence adds value, and the organization makes it easy for an agent to scan and extract key information.

  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 absence of an output schema and annotations, the description is remarkably complete. It covers when to use, all parameters with defaults, an explicit list of return fields, and even edge-case behavior. This is sufficient for an agent to select and invoke the tool correctly.

  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 description coverage is 0%, but the description compensates fully with a dedicated Parameters section. Each parameter has its type, default, and meaning, including the timezone format nuance (integer or 'h:30' string) and the is_solar boolean. This exceeds what the bare schema provides.

  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 opens with a clear statement of what the tool evaluates: auspicious days, hours, 12 Trực, 28 Tú, Tiết Khí, and auspicious directions. It names the specific Vietnamese entities and explicitly lists use cases, distinguishing it from sibling tools like convert_calendar or get_van_han.

  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 clearly states when to use the tool ('Use this tool when users ask to check good/bad days, auspicious hours...') and gives concrete activity examples. However, it does not mention when not to use it or explicitly name alternative sibling tools, so it lacks full exclusion guidance.

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

• convert_calendarA
  5/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden and exceeds it. It explicitly declares 'Side Effects: None. This is a pure mathematical calculation,' and 'Runs entirely locally. No authentication or external rate limits apply.' It also discloses error behavior (returns error dictionary for invalid input). This is comprehensive behavioral disclosure.

  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?

  Though long, the description uses clear markdown sections (Purpose, Side Effects, Prerequisites, Parameter Guidelines, Output Schema) with bullet points. Every sentence conveys necessary details for correct usage. It is front-loaded with the core purpose and critical usage warning, and the formatting makes it scannable. No wasted words.

  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 no annotations, no output schema, and 6 parameters with 0% schema description coverage, the description fully compensates. It provides prerequisites, parameter constraints, expected output keys, error conditions, and operational context (local execution). The agent has everything needed to confidently invoke the tool and interpret results.

  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 zero descriptions (coverage 0%), so the description is the only source of parameter meaning. It fully compensates by explaining every parameter: day/month/year ranges, `from_solar` default and effect, `lunar_leap` conditionality, and the timezone format with examples and rejection of out-of-range values. It also notes interactions between `from_solar` and `lunar_leap`, adding semantics beyond 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 opens with a clear verb+resource statement: 'Convert a date between the Solar (Dương lịch) and Lunar (Âm lịch) calendars.' It also explicitly distinguishes from sibling tools by stating that chart generation tools already handle conversions internally and that this tool is mandatory for transit assessments before `get_van_han`. This fully disambiguates purpose from 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 Guidelines5/5

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

  Provides explicit usage context: 'CRITICAL FOR TRANSIT ASSESSMENTS' with a clear directive to convert Solar periods before calling `get_van_han`. It also states when NOT to use the tool: 'Do NOT use this tool if you only need base chart calculation' and names the alternative tools. This gives the agent complete decision criteria.

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

• get_van_hanA
  5/5.0
  Behavior5/5

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

  With no annotations provided, the description fully discloses behavior: states no side effects ('read-only calculation and does not write to the database or render filesystem files'), local execution with no auth/rate limits, and error behavior ('Returns an error dictionary...'). It also clarifies that current_year/month/day are Lunar, adding critical context beyond defaults.

  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?

  Though lengthy, the description is well-structured with clear sections (Purpose, Side Effects, Prerequisites, Parameter Guidelines, Output Schema, Errors). It is appropriately sized for the tool's complexity (11 parameters, no output schema). The first sentence front-loads the core purpose, and every section provides essential information.

  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 tool's complexity and absence of an output schema, the description is highly complete. It explains the returned dictionary fields (person_details, target_period, transit_stars, dai_han, tieu_han, nguyet_han, nhat_han), includes error conditions, and mentions the critical Lunar conversion prerequisite. This gives an agent everything needed to invoke the tool correctly.

  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 0% description coverage, but the description includes a detailed 'Parameter Guidelines & Interactions' section covering all 11 parameters. It adds meaning beyond the schema: e.g., timezone accepts integer or 'h:30' string, current_day is optional and adds nhat_han, and current_year defaults to the system year. This fully compensates for the schema's lack of descriptions.

  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 opens with a specific verb and resource: 'Calculate transit stars (sao lưu) and active houses (Đại Hạn, Tiểu Hạn, Nguyệt Hạn, Nhật Hạn) for the target Lunar period.' It clearly distinguishes this tool from generate_horoscope by stating get_van_han is for inspecting luck during a specific timeframe versus a static birth chart.

  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 states when to use the tool ('Use this tool to perform transit/vận hạn luck analysis...') and contrasts with alternatives ('Use generate_horoscope to get the static, base birth chart'). Also provides a prerequisite: must convert Solar dates to Lunar using convert_calendar before calling.

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