Server Quality Checklist

Tool Scores

• get_daily_almanacA
  3.7/5.0
  Behavior3/5

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

  No annotations are supplied, so the description carries the burden of disclosing behavior. The read-only nature is implied by the verb 'Get' but not explicitly stated, and the description does not mention output format, error handling, or side-effect guarantees. It does transparently list the returned data categories, which is helpful context.

  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 dense sentence with the core action front-loaded, followed by a long but relevant enumerated list of almanac fields. It is information-dense without padding, though the list could be structured with line breaks for improved readability.

  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?

  With no output schema present, the description compensates by enumerating the main return categories, which is sufficient for a simple one-optional-parameter read-only query. It could clarify the final response shape, but the extensive content list makes the tool's scope effectively complete.

  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 fully documents the single optional date parameter, including its YYYY-MM-DD format, default of today, and New York timezone. The description adds no meaningful parameter-level details beyond the schema, so the baseline of 3 is appropriate given 100% 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 uses a specific verb and resource ('Get the full Chinese almanac for a date') and enumerates the major data categories returned, such as lunar date, day pillar, zodiac clash, auspicious/avoid items, and solar terms. This clearly distinguishes it from sibling tools like get_daily_horoscope or get_solar_terms.

  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 intended use is reasonably clear: use this when you need comprehensive date-specific almanac data. However, it does not explicitly name sibling alternatives or state when to prefer this tool over related ones such as get_solar_terms, get_hour_pillars, or pick_auspicious_dates.

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

• get_solar_termsA
  4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the behavioral disclosure burden. It does well by revealing minute-level precision, the JPL DE440s ephemeris source, an example output value, and the current-year ±1 range. It stops short of describing full output structure or timezone handling, but this is a simple getter.

  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 compact and front-loaded with the core action and resource. The bilingual phrasing is slightly redundant but adds useful context for the intended audience, and every remaining clause contributes precision, example, or constraints.

  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?

  This is a low-complexity single-parameter tool with no output schema, so the description is mostly sufficient: it names the return concept, gives an example, specifies precision, and states the valid range. It could more explicitly state the full output shape or timezone, but nothing critical prevents an agent from calling it correctly.

  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%, and the schema already documents the year parameter with range and free-tier note. The description mostly restates this with 'Range: current year ±1' and adds an example year, so it does not add substantial semantic value 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 states a specific action ('Get the 24 solar terms of a year') and adds precision details, data source (JPL DE440s), and a concrete example. This makes it clearly distinct from sibling tools like get_daily_almanac or get_personal_lucky_hours.

  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 when to use the tool: whenever a full year's solar terms are needed. However, it gives no explicit comparison to sibling tools, no exclusion criteria, and no guidance on when a sibling would be more appropriate.

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

• get_daily_horoscopeA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly describes the return format as '0-100 + tier + 8 life categories,' giving agents a concrete expectation of the response. The verb 'Get' and the context make it clear this is a read-only lookup, though it does not discuss edge cases or error behavior.

  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, information-dense sentence that front-loads the primary purpose and output summary. The sign list is long but relevant and bilingual, so every segment earns its place. It is concise without sacrificing useful detail.

  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 simple read-only tool with two parameters and no output schema, the description covers the essential context: what it returns, which signs it accepts, and the date parameter's default. It does not enumerate the eight life categories, but that level of detail is not required for correct invocation.

  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%, with both parameters already documented with type, format, and defaults. The description adds the Chinese sign translations and reinforces the sign slug list, but this is supplemental rather than essential. It does not fundamentally expand on the schema-provided semantics.

  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 states a specific verb and resource: 'Get the daily luck score for a Chinese zodiac sign.' It clearly scopes the operation to zodiac signs and distinguishes it from sibling tools like get_personal_lucky_hours and get_daily_almanac. The inclusion of the full sign list in English and Chinese leaves no ambiguity about what the tool targets.

  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 the tool is for daily luck scores of Chinese zodiac signs, which naturally differentiates it from sibling tools focused on personal lucky hours, almanacs, hour pillars, solar terms, and auspicious dates. However, it does not explicitly state when NOT to use this tool or name alternatives, so it falls just 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.

• pick_auspicious_datesA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of disclosure. It clearly states the engine's methodology (four-tier spirit arbitration), the ability to accept natural-language synonyms, and the weekend-only filter behavior. It does not describe the return format or pagination, but for a non-destructive date-picking tool these are minor omissions.

  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 front-loaded with the core action and then provides a well-organized list of event types. It is more verbose than the minimum because of bilingual examples, but every element — activity scope, engine, synonyms, weekend filter — contributes directly to correct invocation.

  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 three-parameter tool with no output schema, the description covers the essential selection criteria and behavior. It lists all supported activities, explains the engine's arbitration approach, and documents synonym handling. The 'days' parameter is covered by the schema, and the lack of a return-value description is acceptable given the tool's straightforward 'pick dates' purpose.

  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 schema already documents all three parameters. The description adds value by reinforcing the synonym flexibility for 'activity' and the weekend filter, but it does not add meaningful detail about the 'days' parameter beyond what the schema states. Baseline 3 is appropriate.

  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 pair, 'Pick the best upcoming dates for a real-life event,' and enumerates the full set of supported activities (weddings, moving, openings, etc.). It also names the engine behind it, making the tool's purpose unmistakable and clearly distinct from sibling tools like get_daily_horoscope or get_daily_almanac.

  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 gives clear context on when to use the tool via the exhaustive activity list and mentions synonym support, so an agent can easily match user requests to this tool. It does not explicitly state when not to use it or point to an alternative, but the scope is concrete enough that selection is unambiguous in most cases.

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

• get_hour_pillarsA
  4.2/5.0
  Behavior4/5

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

  With no annotations present, the description carries the behavioral burden and largely meets it: it discloses the fixed 12-pillar output, the two classification buckets, and enumerates all six auspicious and six caution deities so an agent knows what categories to expect. Minor gaps remain — no return format or timezone note — but the fixed, predictable structure of hour pillars keeps these low-risk.

  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 compact sentence that front-loads the core action and resource, then layers the classification detail. The bilingual Chinese keyword aids matching, and every element — the pillar list, the deity names, the auspicious/caution split — earns its place with no filler.

  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 low-complexity tool with one parameter, no annotations, and no output schema, the description supplies sufficient expectations: 12 items, each assigned to an auspicious or caution deity group. It stops short of specifying the JSON shape or edge-case behavior, but the fixed 12-pillar nature makes correct invocation and result interpretation achievable without it.

  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 single date parameter is fully specified with format and pattern. The description's '某日' phrasing merely reaffirms that the date selects the target day, adding no format, range, or syntax information 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.

  Purpose5/5

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

  The description names a specific verb ('Get'), a precise resource ('12 two-hour pillars 子丑寅卯…'), and a distinctive classification scheme (Yellow/Black Belt deities). It differentiates from siblings like get_daily_almanac and get_personal_lucky_hours by its hour-level granularity and the six-vs-six auspicious/caution deity split, so an agent can accurately tell it apart without opening any schema.

  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 frames when this applies — querying the 十二时辰 (two-hour pillar) auspiciousness for a specific date, unlike personal lucky hours or daily-level almanac readings. However, it does not explicitly name alternatives or state exclusion conditions; the routing guidance is inferred from the content, not stated.

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

• get_personal_lucky_hoursA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the transparency burden. It discloses the computation approach (zodiac relations with the day's Yellow/Black Belt hours) and the output semantics (best_hours with 0-10 personal scores). It stops short of detailing return shape, but the read-only nature is reasonably implied by 'Returns.'

  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 core action, then follows with method and output. The bilingual gloss adds clarity without padding.

  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?

  With no output schema, the description helpfully identifies the return concept (best_hours with scores), which is important for a tool with this complexity. A bit more detail about the exact return shape would improve completeness, but the essential invocation and output are clear.

  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 schema already documents both parameters. The description reinforces the role of date and zodiac and adds output meaning, but it does not add parameter syntax or format details beyond what the 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 uses a specific verb ('Rank') and a specific resource ('12 hours of a day for YOUR zodiac sign'), and it explains the underlying method (zodiac relations plus Yellow/Black Belt hours). This clearly distinguishes it from sibling tools like get_daily_horoscope or get_solar_terms.

  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 'for YOUR zodiac sign' and 'personal lucky hours' provide clear context for when this tool is appropriate. It does not explicitly name alternative tools or state when not to use it, but the intended use case is unambiguous.

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

• list_activitiesA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description must carry the behavioral burden. It clearly indicates a read-only listing behavior and specifies the exact content: 'the 8 supported event types with all accepted synonyms.' It does not explicitly state that nothing is mutated or describe output format, but the simple listing behavior is sufficiently disclosed for this low-risk 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, front-loaded sentence that provides the core purpose first and the usage rationale second. The bilingual portion is compact and non-redundant. Every part 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?

  Given the zero-parameter schema, no output schema, and simple listing behavior, the description is complete. It states what is listed, how many items, the language coverage, and how an agent should use it in relation to pick_auspicious_dates. Nothing essential is missing for correct 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?

  The tool has zero parameters, so the schema provides no parameter documentation. The description adds meaningful context by explaining that the output validates the 'activity argument' for another tool, which tells an agent exactly how to use the returned values. This exceeds the baseline expected for a no-parameter tool.

  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 specific verb and resource: 'List the 8 supported event types with all accepted synonyms (EN/CN)'. It also differentiates itself from siblings by framing the tool as a validation lookup for pick_auspicious_dates, which makes its unique purpose unmistakable.

  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 gives clear guidance: 'use this to validate the activity argument before calling pick_auspicious_dates.' It identifies the appropriate context and indicates that this tool is a prerequisite step, though it does not explicitly state when not to use it or contrast it with other siblings.

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