Server Quality Checklist

Tool Scores

• delete_memoryA
  3.8/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It covers privacy and cleanup patterns but does not mention irreversibility, authentication, 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.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Well-structured with clear headings. Front-loaded with purpose, then guidelines, privacy, and cleanup. Each section adds value, though could be slightly more concise.

  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?

  Covers main use cases but lacks explanation of return values or error handling (e.g., invalid id). Adequate for a simple deletion tool but incomplete for edge 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?

  Only one parameter 'id' with schema description already clear. The description adds no extra meaning beyond schema, and coverage is 100%.

  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 'Remove' and the resource 'specific memory', distinguishing it from siblings like delete_all_memories. It also specifies contexts where deletion is appropriate.

  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 'When to Use' section provides specific scenarios such as user requests deletion, redundancy, or error. It implicitly excludes other operations but does not explicitly name alternatives.

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

• search_memoriesA
  3.8/5.0
  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 describes retrieval behavior but does not disclose side effects, permissions, or safety profile. It is adequate but not comprehensive.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness2/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is overly verbose with extensive bullet points and patterns. While informative, it could be more concise and front-loaded. Many details could be streamlined.

  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?

  No output schema exists, so description should explain return values but does not. It covers usage patterns well but lacks information on result format. Adequate but not fully complete.

  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%, so baseline is 3. The description adds practical advice like 'lower limits (1-3) for specific lookups, higher limits (5-10) for broad context' and mentions the default limit, adding 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 clearly states 'Query stored memories to retrieve relevant context' using a specific verb and resource. It distinguishes itself from sibling tools like add_memory, delete_memory, etc.

  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 extensive guidelines including triggers, pre-execution recall patterns, proactive search, and limit recommendations. It does not explicitly exclude when not to use, but gives clear usage context.

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

• get_memoryA
  4.1/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It states the return includes 'full memory details including metadata, timestamps, and the stored content' but does not mention error handling (e.g., if ID not found) or other behavioral traits like idempotency.

  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?

  Description is well-structured with clear sections, concise (about 5 sentences), and every sentence adds 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 retrieval tool with 1 parameter and no output schema, the description provides enough context: when to use, what it returns, and relationship to siblings. Complete for the complexity level.

  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 1 parameter 'id' with description 'The memory ID to retrieve.' Schema coverage is 100%. Description does not add new parameter info beyond schema; 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?

  Description clearly states 'Retrieve a specific memory by its ID.' It specifies the verb (retrieve) and resource (memory by ID), and distinguishes from sibling tools like search_memories.

  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?

  Provides explicit 'When to Use' and 'Pre-Execution Recall' sections, explaining when to use this tool (e.g., have memory ID) and recommending search_memories when lacking an ID. Lacks explicit when-not-to-use 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.

• add_memoryA
  4.2/5.0
  Behavior4/5

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

  No annotations provided, but the description discloses deduplication behavior ('Search before adding', 'Prefer UPDATING existing memories') and storage pattern. Does not mention return value or side effects, but acceptable for a simple store tool.

  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?

  Well-structured with headings and bullet points, front-loaded with purpose. Slightly long but every sentence adds value. Could be shorter, but not verbose.

  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?

  Covers usage scenarios, deduplication, storage pattern, and parameter guidance. No missing information given the tool's simplicity and lack of output schema.

  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% with all parameters described. The description adds value for the 'text' parameter by advising to write 'clear, searchable statements'. No additional detail for other params beyond 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 'Save important information to long-term memory' and provides specific examples of what to store (preferences, context, decisions). It distinguishes from siblings like search_memories, update_memory, and delete_memory.

  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 'When to Use' section explicitly lists categories of information (preferences, personal context, project patterns). The 'Post-Response Storage Pattern' gives procedural guidance. Missing explicit when-not-to-use, but adequate.

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

• update_memoryA
  4.5/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. It explains that text replaces content entirely, metadata preserves linkage, and discusses update vs add decision. Lacks details on permissions or failure modes, but adequate for the 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?

  Well-structured with sections, front-loaded purpose. Slightly verbose but each section is informative. No wasted sentences.

  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 output schema, description covers usage scenarios, storage decisions, and parameter behavior. Lacks return value details but sufficient for a simple update tool.

  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%, baseline 3. Description adds value by explaining that text replaces previous content entirely and metadata only supports runId, and that id is from get_memory or search results.

  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 clearly states 'Update an existing memory when information changes or needs correction.' Uses specific verb+resource, and differentiates from siblings like add_memory and delete_memory.

  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?

  Provides explicit when-to-use scenarios: same fact changes, more precise info, user corrections, correcting errors. Also includes post-response correction pattern and storage decision for clarification.

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

• delete_all_memoriesA
  4.6/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. Clearly states destructive and irreversible nature, and behavior difference with/without agent_id. Pre-deletion recommendation adds context. Lacks mention of return value or side effects, but for a delete tool this is 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?

  Description is moderately verbose with bullet points and sections, but each part earns its place (use cases, caution, pre-deletion recommendations). Could be trimmed slightly, but front-loaded first sentence conveys core purpose.

  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 output schema and two optional parameters, description covers use cases, caution, and parameter behavior. Lacks detail on return value or default user_id, but sufficient for a destructive bulk operation. Siblings are well-differentiated.

  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?

  Schema coverage 100%, but description adds significant value: explains how agent_id filters to a session, and implies user_id defaults. Clarifies behavior beyond schema descriptions, enabling correct tool usage.

  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?

  Clearly states 'Bulk delete all memories for a user, optionally filtered to a specific session.' The verb 'bulk delete' and resource 'memories' are specific. Differentiates from sibling 'delete_memory' which deletes a single memory.

  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?

  Explicit use cases listed (fresh start, privacy wipe, cleanup, memory reset). Caution warns of destructiveness and irreversibility, advising confirmation. Recommends targeted delete as alternative, distinguishing from delete_memory.

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