Server Quality Checklist

Tool Scores

• memory_searchA
  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 full burden. It discloses that the tool 'Supports both semantic (meaning-based) and keyword search,' which adds behavioral context. However, it does not explicitly state that it is read-only, what the return value looks like, or any side effects. Moderate but not rich transparency.

  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 sentences, front-loaded with the core purpose, then usage context, then capability. Every sentence adds value and there is no redundancy or fluff.

  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 provides purpose and usage guidance, but since there is no output schema, it does not explain what the tool returns (e.g., list of memories, ordering, pagination). It also does not mention the limit/tags parameters, though these are documented in the schema. Adequate but with some gaps.

  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 detailed descriptions for query, tags, and limit. The description repeats the semantic/keyword matching already present in the query parameter description, so it adds no new meaning beyond what the schema provides.

  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 'Search your memory for relevant information' with a specific verb and resource. It also lists concrete use cases (start of task, checking past discussions, referencing past work) that distinguish it from sibling tools like memory_get, memory_store, 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?

  Provides explicit guidance on when to use: 'Use this at the start of a task to recall relevant context, when you need to check if something was previously discussed, or when the user references past work.' However, it does not explicitly mention when not to use it or alternatives, but the listed use cases give clear context.

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

• memory_deleteA
  4.3/5.0
  Behavior4/5

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

  Given no annotations are provided, the description carries the burden of behavioral disclosure. It explicitly states 'This action is irreversible,' which is a critical behavioral trait for a destructive tool. It doesn't detail additional effects, but the irreversibility warning is a strong disclosure.

  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 concise, with two sentences that cover purpose, usage, and a critical warning. Every sentence earns its place with no redundant information.

  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 delete operation with one parameter and no output schema, the description is complete: it states what is deleted, when to use it, and warns about irreversibility. The context is fully covered without needing additional detail.

  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 fully describes the 'id' parameter as 'The memory ID to delete.' The description adds no additional semantic information beyond this, so with 100% schema coverage, the baseline score of 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 uses a specific verb ('Delete') and a clear resource ('a memory'), directly stating its function. It distinguishes itself from sibling tools like memory_get, memory_store, and memory_update by focusing on removal.

  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 by stating 'Use this to clean up outdated information' and specifying the condition 'no longer relevant or accurate.' However, it does not explicitly mention alternatives or when not to use this tool, so it falls short of full guidance.

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

• memory_updateA
  4.4/5.0
  Behavior4/5

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

  With no annotations available, the description carries the full burden. It reveals key behavioral traits: it is a direct field update, not re-processed through reconciliation, and requires at least one field to update beyond the ID. This goes beyond the schema by clarifying operational semantics, though it doesn't address permissions or return 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 three sentences long, front-loaded with the core action, and every sentence provides necessary information. There is no redundancy or fluff, making it efficient and well-structured.

  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's simplicity and complete schema descriptions, the description covers purpose, usage, behavioral caveats, and parameter constraints. It does not mention return values, but with no output schema this is a minor gap. Overall, it is sufficiently complete for an AI agent to select and invoke the tool 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 schema covers 100% of parameters with descriptions, so baseline is 3. The description adds a crucial semantic constraint: 'Provide the memory ID and at least one field to update,' which is not enforced by the schema (only id is required). This clarifies invocation requirements and adds 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 the action: 'Update an existing memory.' It distinguishes the tool from siblings by specifying it modifies existing memories rather than creating, retrieving, deleting, or searching. The verb 'update' plus resource 'memory' is specific 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 provides explicit usage context: 'Use this when information has changed, needs correction, or should be enriched with additional context.' It also sets expectations with 'direct field update' and notes the need for at least one field. However, it does not explicitly name alternative tools or state when not to use it, so it's just under a full 5.

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

• memory_getA
  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. The verb 'retrieve' clearly indicates a read-only, non-destructive operation, which is behaviorally transparent for a simple getter. It also mentions that it returns 'full content,' setting expectations for the response, though it does not detail edge cases like missing IDs.

  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 the main action front-loaded. The first sentence states the purpose; the second clarifies usage. No redundant information or filler words. Every sentence serves a distinct function: definition and usage guidance.

  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 tool with one parameter and no output schema, the description adequately covers the essentials: what it does, when to use it, and what the input should be. It references sibling tools implicitly by mentioning 'previous search,' providing context for integration. The simplicity of the operation doesn't demand more detail.

  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 input schema has 100% coverage for the single parameter 'id', describing it as a UUID. The tool description adds context beyond the schema by stating the ID comes from 'a previous search,' helping the agent understand the provenance and relationship to sibling tools. This adds meaningful usage semantics.

  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: 'Retrieve a specific memory by its ID.' It uses a specific verb with a resource and scope, distinguishing it from siblings like memory_search (which finds memories without an ID) and memory_delete/memory_update (which modify memories). The additional clause 'need the full content' further clarifies its purpose.

  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?

  The description explicitly provides usage guidance: 'Use this when you have a memory ID from a previous search and need the full content.' This tells the agent the prerequisite (an existing memory ID) and the typical workflow (search first, then retrieve). It implies that this tool is not for initial discovery, contrasting with memory_search.

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

• memory_storeA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description fully discloses key behaviors: asynchronous processing, non-verbatim storage, searchability delay, and the absence of the stored memory's ID in the response. It also implicitly warns about the processing pipeline, exceeding expectations for transparency.

  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 front-loaded with the core action and expands into necessary behavioral disclosures and usage guidance. Each sentence adds distinct value: purpose, async behavior, appropriate content, exclusions, and ID caveat. No redundancy or filler.

  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 the absence of annotations and output schema, the description carries the full contextual burden and does so admirably: it explains the async processing, searchability delay, appropriate content, exclusions, and the response limitation regarding IDs. The schema covers parameters comprehensively, so no additional parameter context is needed.

  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 parameters with specific examples and guidance. The description adds only tangential context (async processing) that affects content meaning but does not enhance understanding of individual parameters. 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 states a clear verb ('Store') and resource ('a new memory'), explicitly distinguishing it from sibling memory tools (get/delete/search/update) by focusing on creation. It also clarifies the async behavior and non-verbatim storage, making the purpose specific 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 Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides explicit usage criteria with concrete examples of appropriate content (user preferences, project conventions, important decisions) and explicit exclusions (trivial/transient info). It also directs users to memory_search for subsequent updates/deletes, clearly demarcating when not to use this tool.

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