Server Quality Checklist

Tool Scores

• interpretation_templateA
  3.9/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It uses the verb 'Return', which implies a safe read operation, but it does not explicitly state that it is non-destructive or list any side effects. It does add context about the template being shared + per-skill and the intended usage phase, which is helpful but not exhaustive.

  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 that immediately states the action and resource. Every word contributes value, and it is front-loaded with the primary purpose. No unnecessary detail or repetition.

  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?

  For a tool with one optional parameter, no annotations, and no output schema, the description provides enough to understand the basic purpose and usage timing. However, it does not describe the structure of the returned template or any edge-case behavior (e.g., what happens when 'skill' is omitted). It is minimally sufficient but leaves some ambiguity.

  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 schema has one parameter with an enum but no description (0% schema description coverage). The description partially compensates by mentioning 'shared + per-skill', which hints that the 'skill' parameter selects between shared and skill-specific templates. However, it does not explicitly explain the parameter name, default behavior, or value meanings beyond what the enum provides. Adequate but with a gap.

  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 ('Return') and a clear resource ('interpretation template'). It also clarifies a key distinction by mentioning 'shared + per-skill', which differentiates this tool from the sibling casting/drawing tools. It fully states what the tool does.

  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 usage context: 'before writing an interpretation'. This implies the tool is used as a prerequisite for interpretation-writing. However, it does not explicitly mention alternatives or when not to use it, so it lacks exclusions. Overall, the timing is clearly stated.

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

• xiaoliuren_castA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral burden. It does state a critical integrity rule, 'The host MUST NOT invent the cast', and flags the optional lunar-python dependency. It does not disclose side effects, permissions, error conditions, or whether the result is deterministic, so behavioral disclosure is only partial.

  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 tight sentences deliver the purpose, the no-invention constraint, and the mode-dependent input requirements with no filler. Important information is front-loaded and every clause adds value.

  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 output schema covers return values, and the description covers method-to-parameter mapping and the dependency caveat. Still, the ambiguity between method=time and method=lunar_time, plus the unstated lunar meaning of month/day/hour, leaves real gaps for an agent trying to select the correct invocation.

  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 description coverage is only 40%, and the description compensates by mapping methods to required parameters: numbers needs month/day/hour, while time modes need datetime. This adds conditional meaning beyond the schema, though it leaves the lunar-calendar basis of the numeric inputs implicit.

  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 opening phrase 'Cast Xiao Liu Ren (小六壬)' uses a specific verb and resource, and the subject clearly separates it from sibling tools such as bazi_cast, tarot_draw, and iching_cast. The rest of the description clarifies the casting modes rather than blurring the purpose.

  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 gives concrete conditions for method=numbers versus method=time/lunar_time, so an agent knows which parameter group is needed. However, it does not explain the difference between method=time and method=lunar_time beyond the dependency, and it never tells an agent when to choose this tool over the sibling divination tools.

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

• tarot_drawA
  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 burden of behavioral disclosure. It reveals that the shuffle is audited and strongly instructs the host not to invent the draw, which is critical for correct use. It stops short of describing output semantics, but the output schema likely handles that.

  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 three tight sentences with no filler. It front-loads the purpose, then supplies critical behavioral and usage guidance. Every sentence adds value.

  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 covers core draw behavior and seed usage, but for a 4-parameter tool with no annotations, it omits explanation of spread types (decision, creative, project) and the meaning of reversals. These gaps reduce completeness despite the output schema.

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

  Parameters2/5

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

  Schema covers `deck` and `seed` (50%), but the description only restates `seed`'s test/demo purpose already in the schema, adding no new meaning. It fails to explain `spread` and `reversals`, which have no schema descriptions, so the low coverage is not compensated.

  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 'Draw tarot cards', a specific verb and resource, and adds 'audited Fisher-Yates shuffle' to distinguish it from other divination tools. Sibling tools like iching_cast and xiaoliuren_cast are clearly different systems, so this uniquely identifies the tool's purpose.

  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 omit `seed` for real readings versus using seeded mode for tests/demos, which is an important usage guideline. It does not explicitly mention alternatives or when not to use the tool, but the distinct sibling names make that less critical.

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

• bazi_castA
  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 full burden. It adds meaningful behavioral guardrails: the host MUST NOT invent pillars, stems, branches, or wuxing, and it discloses the lunar-python dependency. It does not describe the failure mode if the dependency is missing, but this is still strong behavioral disclosure for a computation-heavy 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 two sentences with no filler: it front-loads the core action and resource, then states the critical operational constraints. Every sentence earns its place, and the result is compact without sacrificing important 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?

  Given the presence of an output schema and fully covered parameters, the description adequately covers the human-guardrail and dependency context. It could go further by addressing edge cases like the Zi-hour day boundary or missing-dependency behavior, but the current combination is sufficient for an agent to invoke the tool correctly in most cases.

  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 no parameter-specific meaning beyond what the schema provides, such as the exact-time requirement for the hour pillar and longitude enabling true-solar-time correction. 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 ('Cast') and names the exact resource ('Bazi (八字 / Four Pillars) chart') plus the required input format ('Gregorian birth datetime'). This clearly differentiates it from sibling tools like tarot_draw, iching_cast, and xiaoliuren_cast, which represent different divination systems.

  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?

  While the description does not explicitly name sibling alternatives, it establishes a clear trigger scenario: casting a Bazi chart from a Gregorian birth datetime, with exact birth time and optional timezone/longitude prerequisites. The context is clear enough for an agent to know when this tool applies, though explicit 'use X instead' guidance is absent.

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

• iching_castA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of disclosing behavioral traits. It adds critical transparency by prohibiting invented casts and explaining the manual_lines requirement for manual method. This goes beyond the schema by highlighting a key safety rule. It does not cover return format, but an output schema exists, reducing that need.

  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 deliver the essential information without redundancy. The instruction is front-loaded, and every phrase earns its place, covering core action, a critical constraint, and parameter guidance.

  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 has an output schema and moderate complexity, the description covers the key aspects: action, methods, and a crucial anti-hallucination rule. It does not explain the seed parameter's purpose beyond the schema, but the schema already marks it as optional test/demo. Overall, it is sufficiently complete for selection and invocation.

  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 67%, with seed and manual_lines documented. The description adds meaning by explaining the method enum values and the conditional requirement for manual_lines when method=manual. This clarifies relationships between parameters beyond the schema's individual 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 clearly states the tool's function: 'Cast an I Ching hexagram.' The verb 'cast' and resource 'I Ching hexagram' are specific and unambiguous. It naturally differentiates from sibling tools like tarot_draw and bazi_cast, which target different divination systems.

  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 usage constraints: 'The host MUST NOT invent the cast' and specifies valid methods ('coins, yarrow, or manual'). It also clarifies the dependency between method and manual_lines. However, it does not explicitly discuss when to choose this tool over alternatives, though the context implies it.

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