Server Quality Checklist

Tool Scores

• review_cardA
  3.6/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the transparency burden. It clearly indicates a user-initiated recording of a review result, but does not disclose side effects such as updating the card's review schedule, overwriting previous results, or required permissions.

  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 concise sentence that starts with the core action and includes necessary parameter semantics. There is no redundancy or filler.

  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 simple 2-parameter tool the description covers the main call intent and parameter semantics, but it does not mention side effects such as updating the card's next review time or whether an existing review record is overwritten.

  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 description adds meaning beyond the schema by defining the three possible values of result (remember/fuzzy/forgot) and stating that the assessment is user self-reported. The id parameter is already described in the schema as the card id.

  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 states a specific action ('记录一次复习结果') with a clear object and context. It does not explicitly contrast with sibling tools like save_card or claim_card, but the purpose is unambiguous from the tool name and description.

  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 this tool—after a user completes a review and self-assesses their recall. However, it does not explicitly mention alternatives or conditions such as 'use this instead of save_card when logging a review outcome.'

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

• search_cardsA
  3.9/5.0
  Behavior3/5

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

  In the absence of annotations, the description explains the retrieval behavior: it takes symptoms/keywords, returns relevant cards, and instructs using them as context. However, it does not disclose edge behaviors such as no-result handling, whether the operation is read-only, or any rate limits or permission requirements.

  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 three sentences and opens with the key instruction on when to call. It is well-structured and economical, though the examples in the second sentence partly duplicate the schema's query description.

  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 2-parameter tool with no output schema, the description covers what to pass, what to expect back, and how to use the result in answer generation. It is missing an explicit statement on what to do when there are no matching cards, but overall it is sufficient 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?

  The schema already describes both parameters at 100% coverage, giving the baseline of 3. The description adds example keywords for the query, but no additional semantic detail for the limit parameter or any supplemental explanation 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 clearly states the tool retrieves the user's historical troubleshooting cards and returns the most relevant ones for context, which is a specific verb+resource pairing. It is distinct from siblings like save_card, delete_card, and claim_card because it focuses on search/retrieval of existing history.

  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 says to call before troubleshooting any issue and to pass symptoms or keywords, which is a strong usage trigger. It also says to favor the returned historical context in answers, but it does not name alternatives or describe when this tool should not be used.

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

• delete_cardA
  4/5.0
  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 discloses the confirmation requirement, which is a meaningful behavioral trait, but it does not state the consequence (permanent removal) or any other side effects. The confirmation implies irreversibility, but explicit disclosure would be stronger.

  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, with the primary purpose and usage condition front-loaded, followed by the confirmation requirement. No wasted words.

  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 single-parameter delete tool, the description covers the purpose, usage condition, and a critical safety step. It could explicitly mention that deletion is permanent or irreversible, but the confirmation requirement largely covers this. Overall adequate for the tool's simplicity.

  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% and the parameter description clearly explains the 'id' field. The description adds no extra parameter information, but none is needed; 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?

  The description clearly states the action ('delete a card') with a specific resource and includes an explicit trigger condition ('when the user explicitly asks to delete'), distinguishing it from sibling tools. The example phrase further clarifies intent.

  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 specifies the exact condition for use (explicit user request) and provides a safety guideline (confirm before deleting). It does not explicitly state when not to use, but given it is the only delete tool, this is acceptable.

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

• claim_cardA
  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 disclosure. It states that the card is promoted to the user's card, enters the review queue tomorrow, and the anchor gets merged only at this moment. It does not mention permissions, reversibility, or failure scenarios, but covers the primary state changes well.

  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: target type, outcome, timing, and trigger are all included in two focused clauses. Every sentence carries essential information 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 this is a simple one-parameter tool with no output schema or annotations, the description addresses the main user-visible effects and call trigger. It could detail return values or preconditions, but for a direct 'claim' action, the context is sufficiently 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 schema already describes the single `id` parameter with 100% coverage. The tool description refines that the id belongs to a ref=true card, which adds slight context, but it doesn't significantly expand beyond what's in 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 names a specific verb and resource: '认领一张参考卡（ref=true 的包卡）' and explains the conversion to the user's card. It clearly distinguishes claim_card from sibling tools like review_card or delete_card by indicating the promotion/ownership action.

  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 provides an explicit trigger: call this when the user clicks '认领/收编' in the detail panel. It doesn't list exclusions or alternatives, but the UI condition is concrete enough for an agent to decide when to invoke it.

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

• due_cardsA
  4.2/5.0
  Behavior3/5

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

  No annotations exist, so the description carries the full burden. It does disclose the output nature ('复习卡片'/'复习清单' – a list of due cards) and implies a non-destructive read operation with '获取'. However, it does not explicitly state whether it modifies state, requires authentication, or what '点亮式' visually means, leaving some behavior implied rather than explicit.

  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 sentences: first states what the tool does, second states when to call it. No redundant words, front-loaded with the primary purpose. This is an efficient, well-structured definition.

  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 zero-parameter, simple retrieval tool, the description sufficiently covers the purpose and triggering condition. Without an output schema, it doesn't fully describe the return structure, but the phrase '复习清单' makes it clear the result is a list, which is enough given 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 0 parameters, and schema description coverage is trivially 100% (empty schema). The description contributes no parameter details because there are none, which matches the baseline for 0-parameter tools. All needed information is already present.

  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 ('获取今天到期的复习卡片' – get review cards due today) with a clear resource ('复习卡片') and scope ('今天到期'). It also names the trigger phrases, and the wording distinguishes it from siblings like search_cards, review_card, and weekly_report by focusing on the 'today + due' use case.

  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 explicitly tells when to use the tool: when the user says '复习' (review) or '今天该复习什么' (what should I review today). This is clear context for when to invoke it, though it does not explicitly mention alternatives or exclusions (e.g., 'not for weekly reports').

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

• log_topicA
  4.2/5.0
  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 goes beyond the schema by revealing that same-day entries are automatically merged, that entries are limited to 40 characters, and that the log serves future recall. It does not detail mutation side effects or return behavior, but for a lightweight logging tool the disclosed traits are sufficient.

  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 organized into clear sections: action, merging behavior, purpose, call timing, and an example. It is somewhat longer than strictly necessary, but every sentence adds practical information and the main action is front-loaded.

  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 only two parameters, no output schema, and no annotations, the description is complete enough for an agent to know when to call the tool, what to pass, what length constraint applies, and what the tool does with the input. The example further disambiguates the expected text format.

  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 baseline is 3. The description adds a concrete example and restates the 40-character limit, but it does not provide additional semantic detail beyond the schema for either 'text' or 'project'.

  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 ('记录对话流水', record conversation log) and clearly distinguishes the tool from sibling card-management tools by stating it captures a short line of what was asked/solved. The purpose is concrete and unambiguous.

  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 explicit call timing: record when a topic wraps up, and backfill when the user says the session is ending. This is clear contextual guidance, though it does not explicitly state when not to use the tool or name alternatives. The sibling names make the distinction fairly obvious.

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

• save_cardA
  4.5/5.0
  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 of behavioral disclosure. It explains the tool's core value (compressing a long conversation into a short card), discloses that anchors are automatically merged server-side, and specifies a post-call confirmation message to show the user. This is behaviorally informative without annotations.

  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 purpose and trigger timing, followed by a clean type-by-type breakdown. It is fairly long, but the length is justified by the need to define three distinct card types and their field semantics. A slightly tighter structure could improve scannability, but there is little waste.

  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 creation tool with 9 parameters, 4 required, and no output schema, the description covers what the tool does, when to trigger it, how to map conversation content into fields, and what to output after saving. It also explains the optional ctx coordinates and the anchoring behavior, so an agent has enough context to invoke it 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?

  Although schema coverage is 100%, the description adds substantial meaning beyond the schema: it maps each card type to specific field interpretations, gives constraints like checks 2-4 items with verb-first steps, anchors 1-4 words, and clarifies that symptom/checks/rootCause mean different things per type. This is far beyond a baseline schema-only definition.

  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: '沉淀成卡' (distill into a card) when AI collaboration produces content worth long-term memory. It further defines three concrete card types (debug, knowledge, decision), making the tool's purpose unambiguous and distinct from sibling tools like search_cards, review_card, or delete_card.

  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 explicit trigger conditions: call proactively after solving a bug, explaining a concept, or making a decision; also trigger on user phrases like '存一下', '今天就到这', or '收尾'. It covers when to use the tool well, though it does not explicitly state when not to use it or name alternative sibling tools.

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

• install_packA
  4.6/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries full responsibility—and it delivers. It discloses that cards enter in ref state, are searchable, appear in 3D view, are excluded from the review queue, and only become active after the user claims them.

  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?

  Every sentence earns its place: scope, behavioral effect, lifecycle, and format are packed into a compact description with no filler. The most important facts appear early.

  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 there is no output schema or annotations, the description covers the tool's purpose, its lifecycle effects, and its data shape. It lacks explicit return/outcome behavior and preconditions, but for an install-style tool the provided context is largely sufficient.

  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 names the pack parameter, and the description adds the full pack shape including nested card fields, optionality markers, and the anchors field. This adds genuine semantic value beyond the schema, though field-level details like anchors are not deeply explained.

  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?

  Uses a specific verb and resource: installing an experience pack (整包进库). It distinguishes the behavior from save_card by emphasizing batch import, domain independence, and ref-state lifecycle.

  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 makes clear this is for bulk-importing someone else's experience pack and explains the resulting card lifecycle, implying it is not for creating a single active card. It does not explicitly name save_card or claim_card as alternatives, but the context strongly signals the distinction.

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

• weekly_reportA
  4.7/5.0
  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 discloses that the operation is pure local statistics with zero dependencies and specifies the four output lists precisely. It does not explicitly state 'read-only', but the framing strongly implies a safe, side-effect-free computation.

  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 every segment earns its place: purpose, data window, four list definitions, trigger phrases, and the narrative-writing instruction. The numbered list improves scanability and keeps the description structured.

  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 no parameters and no output schema, the description fully explains what the tool returns (the four lists with their criteria) and how the agent should use that output. Nothing necessary for correct invocation or follow-up is missing.

  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?

  There are zero parameters, so the 100% schema coverage is vacuous and no parameter documentation is needed. The description still adds useful semantic context by defining the data window: comparing the current 7 days against the prior 7 days.

  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: generating a personal evolution weekly report that compares the last 7 days to the previous 7 days, and lists four specific output lists. This clearly distinguishes it from sibling tools like save_card and review_card.

  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?

  It explicitly names trigger phrases ('复盘', '周报', '我进步了吗') and instructs the agent to write a narrative weekly report after receiving the statistics, not just repeat numbers. This gives clear when-to-use context and expected follow-up behavior.

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