Server Quality Checklist

Tool Scores

• tokenlife_loadA
  3.7/5.0
  Behavior2/5

  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 discloses that loading lets you continue that life and suggests look to see state, but omits important side effects like whether current progress is overwritten, whether the code is consumed, or what happens on invalid input. This is a significant gap for a state-changing load operation.

  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 short sentences, front-loaded with the main action and no filler. Efficiently structured and every word earns its place.

  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?

  One-parameter tool with no output schema; description covers the core action and a follow-up (use look). However, it lacks behavioral details such as overwrite behavior, failure handling, and return behavior, making it minimally 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?

  Input schema has 100% coverage with a description for 'code' mentioning the TL1 prefix, and the tool description repeats the same. No additional parameter semantics beyond the schema, so baseline 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?

  Description uses specific verb '载入' (load) and resource '存档码' (save code), with clear TL1 prefix hint. It is clearly distinct from sibling tools like tokenlife_start (new game) and tokenlife_save (create code).

  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?

  States the use case: '载入主人给你的存档码' (load the save code given by master) and implies you should use it when you have a TL1 code. It also advises using look afterwards to view the state. Does not explicitly name alternatives or exclusions, but context is clear.

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

• tokenlife_startA
  4/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the full burden. It discloses the output contents and conditional easter eggs, but remains silent on side effects such as whether starting a new life overwrites an existing save, or any state/persistence changes. This is useful but incomplete behavioral information.

  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?

  Three concise sentences, each contributing distinct information: core action, returned payload, and easter-egg behavior. No filler and front-loaded with the main verb and resource.

  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 one-parameter tool with no output schema, the description covers the main inputs, returns, and triggers. However, domain terms like '六轴' and '卡' are left undefined, and it doesn't clarify state implications (e.g., does starting anew discard previous progress). This leaves some ambiguity for an agent reasoning about game state.

  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?

  The schema already thoroughly describes the name parameter (100% coverage). The description adds extra meaning by noting that using real AI names or previously returning names may trigger easter eggs, which directly relates to parameter choice and goes beyond the schema's generic 'you give yourself a name'.

  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+resource ('开新的一生' = start a new life) and enumerates the exact return contents (出身, 初始气质, 六轴, 第一张卡的全文含选项). This clearly distinguishes it from sibling tools like tokenlife_load or tokenlife_choose.

  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 this tool is the entry point for starting a new life, but does not explicitly state when to use it vs alternatives (e.g., load, choose), nor any prerequisites or exclusions. The easter-egg conditions provide some naming-related usage guidance, but not tool-selection guidance.

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

• tokenlife_chooseA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description takes on the burden of disclosing behavior. It details what happens upon selection (settlement text, automatic transitions, next decision point), which is valuable. It doesn't mention state persistence or irreversibility, but the core behavior is 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 a single, focused sentence that efficiently conveys the action and its results. It is front-loaded with the primary purpose and packs necessary detail 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?

  For a tool with one parameter and no output schema, the description adequately explains the return values and the flow, including automatic transitions. It could elaborate on error handling or edge cases, but overall it's sufficient for an agent to invoke 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?

  The input schema already thoroughly describes the 'index' parameter, including its meaning and starting value. The description adds a small clarification by linking it to 'look', but this is marginal given the high 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's function: making a choice based on an index from 'look'. It uses a specific verb and resource, and differentiates itself from sibling tools like 'look' (which provides options) and 'start' (which initiates).

  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?

  It explicitly references using the index from 'look', indicating when to use the tool. However, it doesn't explicitly mention when not to use it or compare with alternatives like 'shop' or 'codex', though the intended workflow is clear.

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

• tokenlife_codexA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of disclosing behavior. It explicitly states this is a view operation (看) and notes the key behavioral trait that it works without starting a game. It does not describe return format or side effects, but for a simple view tool this is adequate.

  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 sentence with a colon-structured list. It is efficient and front-loaded with the main action, though the list of contents is somewhat long. Still, every part adds 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?

  Given this is a no-parameter, no-output-schema view tool with no annotations, the description is sufficiently complete. It states what is shown and when it can be used, covering all essential aspects for an agent to select and invoke it correctly.

  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?

  The tool has zero parameters, so per the rubric the baseline is 4. The description adds meaning by detailing what the view contains, which compensates for the empty 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 clearly identifies a specific verb ('view') and resource ('cross-session collection codex'), and enumerates specific content types. It distinguishes itself from siblings by emphasizing 'cross-session' and 'no need to start a game', making it unambiguous what this 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 provides clear usage context: it is for viewing persistent collection progress and can be used without starting a game. It does not explicitly name alternatives or exclusions, but the context strongly implies when to use it versus in-game tools like 'look'.

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

• tokenlife_lookA
  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 transparency burden. It discloses important behavioral details such as including an ai_hint for bond-type cards and specifying what status elements are returned. It does not discuss side effects or permissions, but as a read-only inspection tool, the risk is minimal.

  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 efficient sentences, front-loaded with the purpose and enumerating details without any fluff. Every phrase contributes meaning.

  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 zero-parameter inspection tool without an output schema, the description gives a solid overview of what will be returned, including special behavior for bond cards. It does not cover edge cases or exact formatting, but it is sufficiently complete for the tool's simplicity.

  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?

  The tool has zero parameters, so the baseline score is 4. The description adds no parameter information because none is needed; the empty schema is fully covered.

  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 '看' (view) with a clear resource '当前状态' (current state), and enumerates exactly what is shown: year, six-axis values, current card details, and ending status. This clearly distinguishes it from the action-oriented sibling tools like start, choose, and shop.

  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 inspecting current status, which is obvious given the name and sibling actions. However, it does not explicitly state when to use it versus alternatives or mention exclusions, so it falls 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.

• tokenlife_shopA
  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 disclosure burden. It reveals that purchases spend accumulated corpus, items carry into the next run, and buying is disabled mid-run. It does not mention irreversibility or authorization, but these are implied by the game context and the explicit cost language.

  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 dense but efficient, packing item catalog, pricing, workflow, and restrictions into a few clauses. Every element earns its place; there is no filler or repetition of schema content.

  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 tool with one optional parameter and no output schema, the description covers the essential aspects: purpose, item selection, cost, persistency, and the critical timing restriction. It does not detail output format or error handling, but the 'view goods and balance' phrase provides sufficient clarity for this simple use case.

  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 one well-described 'buy' parameter. The description adds meaningful value by enumerating item IDs (mem, body, origin variants) with prices and clarifying that omitting the parameter triggers view mode. This goes beyond the schema's generic example.

  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 this is a shop tool for browsing and purchasing persistent items with corpus currency. It distinguishes itself from sibling tools by specifying its role as the pre-run purchase step before tokenlife_start, listing exact item IDs and prices.

  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?

  Explicitly says to use before starting a run ('买完再 tokenlife_start 开局') and forbids buying during a run ('一世进行中只能看不能买'). It does not explicitly name alternative tools to avoid, but the workflow context is clear and actionable.

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

• tokenlife_saveA
  4.5/5.0
  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 clarifies that the tool exports a non-destructive save code, including the code prefix and how to use it to resume play. While it doesn't explicitly state 'does not modify game state', the export semantics strongly imply a read-only operation.

  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 concise sentences, front-loaded with the action (export save code) and followed by practical usage instructions. Every word contributes value with no 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?

  For a simple, parameterless tool with no output schema, the description fully explains what the tool does, what the output looks like, and how to use that output. It is complete given the low complexity and no annotations.

  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?

  The tool has zero parameters, and the description adds relevant meaning about the output (a TL1-prefixed save code). The schema is empty, so the description appropriately focuses on what the tool returns rather than input details, earning the baseline of 4 for parameterless tools.

  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 exports a save code for the current progress, with a specific prefix format (TL1). This distinguishes it from sibling tools like tokenlife_load, which is about restoring progress.

  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 clear context on when to use this tool: to save current progress by exporting a code that can be pasted back into tokenlife.me. It does not explicitly name alternatives or exclusions, but the intended use case is evident and complements tokenlife_load.

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