Server Quality Checklist

Tool Scores

• update_cardA
  4.1/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden. It discloses that the tool returns a success message with operation details, which is helpful behavioral context. However, it doesn't mention important behavioral traits like whether updates are destructive (e.g., tags REPLACE all existing tags is only in schema), authentication requirements, error handling, or rate limits for a mutation 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 perfectly front-loaded with the core purpose and 4 operations in the first sentence, followed by the return value. Every sentence earns its place by providing essential information without redundancy. The structure is logical and efficiently communicates the tool's capabilities.

  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 complex mutation tool with 8 parameters, nested objects, and no annotations or output schema, the description is adequate but has gaps. It explains the operations and return value, but doesn't cover important contextual details like error conditions, side effects, or how this tool relates to sibling tools. The schema handles parameter documentation well, but the description could provide more behavioral context.

  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 100%, so the schema already documents all parameters thoroughly. The description adds value by summarizing the 4 operations and their purposes, which helps the agent understand the semantic grouping of parameters. However, it doesn't provide additional syntax or format details beyond what's in the schema 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 verb ('Update') and resource ('a card/note in Anki'), and distinguishes this tool from siblings by specifying it supports 4 distinct operations. It goes beyond a simple update to explain the specific operations available, which differentiates it from tools like 'add_card' or 'get_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 provides clear context for when to use each operation (e.g., 'answer' for marking as reviewed, 'update_note' for comprehensive updates), but doesn't explicitly state when NOT to use this tool versus alternatives like 'add_card' for creating new cards. It implies usage through operation descriptions but lacks explicit exclusions or comparisons to sibling tools.

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

• add_cardA
  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 full burden and does well by disclosing key behavioral traits: it specifies the return value ('Returns card ID on success'), reveals formatting constraints ('Use HTML only'), explains media handling ('Media files support URLs or local absolute paths'), and mentions case-sensitivity requirements. It doesn't cover error conditions or rate limits.

  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 efficiently structured with zero wasted sentences. It front-loads the core purpose, then provides essential formatting and media guidelines. Each sentence adds distinct value: creation action, requirements, return value, formatting rules, and media support.

  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 creation tool with no annotations and no output schema, the description provides substantial context: purpose, requirements, return value, formatting constraints, and media handling. It covers the essential behavioral aspects though doesn't address potential errors, authentication needs, or the exact structure of the returned card ID.

  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?

  With 100% schema description coverage, the schema already documents all 6 parameters thoroughly. The description adds minimal parameter semantics beyond the schema - mainly emphasizing the 'fields' object must match note type field names and repeating HTML formatting guidance. This meets the baseline for 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 specific action ('Create a new flashcard in Anki') and identifies the resource ('flashcard'), distinguishing it from siblings like 'batch_add_card' (bulk operation) or 'update_card' (modification). It provides a complete functional overview in the opening sentence.

  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 about when to use this tool by specifying required parameters and formatting requirements, but doesn't explicitly mention when to use alternatives like 'batch_add_card' for multiple cards or 'update_card' for modifications. The guidance is practical but lacks sibling differentiation.

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

• get_due_cardsA
  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 full burden and does well: it discloses the return format (JSON with count and cards array), data structure details (card fields and types), ordering behavior (by due date earliest first), and that it retrieves a specified number of cards. It doesn't mention permissions, rate limits, or error handling, but covers core behavioral aspects adequately.

  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 front-loaded with the core purpose, followed by essential details about return format and ordering. Every sentence adds value: first states what it does, second describes output structure, third specifies card fields, fourth explains ordering. 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 read-only tool with 1 parameter and no output schema, the description provides good completeness: it explains what the tool does, what it returns, and how results are ordered. It could mention if there are authentication requirements or pagination, but covers the essential context well given 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%, so the schema already documents the 'num' parameter fully. The description adds no additional parameter information beyond what's in the schema, but doesn't need to compensate. Baseline 3 is appropriate as the schema handles parameter documentation.

  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 purpose with a specific verb ('Retrieve') and resource ('cards that are due for review'), and distinguishes it from siblings like 'get_card' (single card) and 'get_new_cards' (different card type). It explicitly defines what 'due' means in this context.

  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 usage for reviewing due cards, which differentiates it from siblings like 'add_card' or 'update_card', but doesn't explicitly state when to use this versus alternatives like 'get_new_cards' or provide exclusion criteria. The context is clear but lacks explicit alternatives guidance.

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

• get_new_cardsA
  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 effectively describes the return format (JSON with 'count' and 'cards' array), details of each card (cardId, question, answer, due), and ordering ('by card position in new queue'). This covers key behavioral aspects like output structure and sorting, though it doesn't mention potential errors or side effects.

  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 front-loaded with the core purpose in the first sentence, followed by essential details about the return format and ordering. Every sentence adds value without redundancy, making it efficiently structured and appropriately sized for the tool's complexity.

  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 no annotations and no output schema, the description compensates well by detailing the return format and card structure. It covers the tool's purpose, usage context, and behavioral traits adequately. However, it doesn't mention potential limitations like pagination or error cases, leaving minor gaps for a read operation.

  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 description coverage is 100%, with the parameter 'num' fully documented in the schema as a required positive integer. The description doesn't add any parameter-specific information beyond what the schema provides, so it meets the baseline of 3 where the schema does the heavy lifting.

  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 specific action ('Retrieve new unseen cards that haven't been studied yet'), identifies the resource (cards), and distinguishes it from siblings like 'get_due_cards' by specifying 'new unseen cards' rather than due cards. The verb 'retrieve' is precise and the scope is well-defined.

  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 for when to use this tool ('new unseen cards that haven't been studied yet'), which implicitly differentiates it from siblings like 'get_due_cards' for due cards or 'get_card' for a specific card. However, it doesn't explicitly state when NOT to use it or name alternatives, keeping it at a 4 rather than a 5.

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

• batch_add_cardA
  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 full burden and does well by disclosing key behavioral traits: returns JSON with success/failure counts and error details, processes cards sequentially, allows partial success, and specifies HTML formatting requirements. It doesn't mention rate limits, authentication needs, or whether this is a read-only or destructive operation, but covers the essential execution behavior.

  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 efficiently structured with zero waste. Each sentence adds distinct value: purpose, parameter relationship, return format, efficiency benefit, formatting requirement, and processing behavior. The information is front-loaded and appropriately sized for the tool's complexity.

  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 batch creation tool with no annotations and no output schema, the description provides good contextual completeness. It explains the return format, processing behavior, efficiency rationale, and formatting requirements. The main gap is lack of explicit safety/disruption information (whether this is a read-only or destructive operation), but otherwise covers what's needed for effective use.

  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 fully documents the single 'cards' parameter. The description adds minimal value beyond the schema by mentioning 'same structure as add_card tool' and 'partial success possible', but doesn't provide additional parameter semantics. Baseline 3 is appropriate when schema does the heavy lifting.

  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 verb ('Create multiple flashcards') and resource ('flashcards'), specifies it's a batch operation, and distinguishes it from the sibling 'add_card' tool by mentioning efficiency gains and different behavior. The purpose is specific and well-differentiated.

  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 ('More efficient than calling add_card multiple times') and provides clear context about HTML formatting requirements and sequential processing with partial success. The description gives practical guidance on when this tool is preferable to its alternative.

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

• get_cardA
  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 full burden. It discloses that it returns an array of card objects, lists the specific fields included, and mentions the mutual exclusivity of parameters. However, it lacks details on error handling, pagination, or rate limits, which are relevant for a retrieval 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 front-loaded with the core purpose, followed by parameter rules and return details, then usage context. Every sentence adds value: the first states what it does, the second specifies parameter logic, the third details the return structure, and the fourth explains when to use it.

  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 no annotations and no output schema, the description does well by listing the return fields and usage context. However, it could improve by mentioning potential limitations (e.g., query performance for large result sets) or authentication needs, though it's largely complete for a read operation.

  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 fully documents the two parameters (cardId and query). The description adds minimal value by restating the mutual exclusivity and general purpose, but does not provide additional syntax or format details beyond what the schema includes.

  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 verb 'retrieve' and resource 'detailed card/note information', specifying it returns an array of card objects with enumerated fields. It distinguishes from siblings like get_due_cards and get_new_cards by not limiting to specific card states, and from update_card by being read-only.

  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 states when to use this tool ('to find card/note IDs for update operations or to inspect card details') and provides clear usage rules: 'Provide EITHER cardId OR query (not both)'. This distinguishes it from siblings by indicating it's for retrieval before updates or detailed inspection.

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