Server Quality Checklist

Tool Scores

• recallA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses 'Read-only, fully local semantic search,' indicating no side effects and privacy (local). This is meaningful additional context beyond just 'search' though it could mention potential limitations like semantic match quality.

  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 well-structured with a purpose line, usage guidance, and a clear Args list. It is front-loaded with the key function and every sentence earns its place.

  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?

  The description covers the tool's purpose, usage context, safety (read-only, local), and all parameter details. Since an output schema exists, return value details are not needed. It is complete for a simple retrieval tool.

  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 is 0%, so the description must compensate. It does so thoroughly: query is 'What to look for (a question or topic)', limit is 'Max memories to return (1-50, default 5)', and user_id is 'Namespace to search (default "default")'—adding semantics and defaults not present 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 clearly states the tool's function: 'Search long-term memory for information relevant to a query.' It uses a specific verb and resource, and the read-only nature distinguishes it from sibling tools (remember, forget, reset_memories) that modify 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 description provides explicit when-to-use guidance: 'Call this before answering when the user refers to past context, preferences, or previously-shared facts.' It lacks explicit when-not-to-use or named alternative tools, but the context is clear enough.

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

• rememberA
  4.6/5.0
  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 'Fully local', 'embeds the text with a local model and writes it to a local SQLite file', and 'No LLM call, no network', providing transparency about side effects and operational behavior. It does not describe the return value, but an output schema exists.

  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 well-structured: a one-sentence summary, a brief technical note, and an Args list. Every sentence is purposeful and there is no fluff.

  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 memory store, the description covers purpose, usage, behavior, and parameters. The sibling tools and the straightforward nature of the operation make it sufficiently complete.

  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?

  The schema provides only names and types with no descriptions, but the 'Args' section adds full meaning: 'content' as the text to remember, and 'user_id' as a namespace with default 'default' and guidance to use per end-user. This substantially enriches 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 'Store a fact or note in long-term memory' with a specific verb and resource. It distinguishes from sibling tools (recall, forget, reset_memories) by focusing on the write operation.

  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 'Use this whenever the user tells you something worth remembering across sessions' with concrete examples. However, it does not explicitly name alternatives or state when not to use, 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.

• reset_memoriesA
  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 carries the full burden of behavioral disclosure. It explicitly states 'Destructive and irreversible,' which is the critical safety trait, and further clarifies namespace isolation with 'This never clears other users' namespaces.' This provides strong, directly relevant context beyond what the schema implies.

  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 extremely concise: two sentences of behavioral context plus a brief parameter explanation. Every sentence earns its place, and the most important information ('Delete ALL', 'Destructive and irreversible') 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 the tool's simplicity (one optional parameter, no enums, no nested objects) and the presence of an output schema (which the description needn't explain), the description covers all essential aspects: purpose, destructive nature, parameter semantics, and scope isolation. No critical gaps remain.

  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 0%, so the description must compensate for the single parameter. It does so by explaining user_id as a 'Namespace to clear' and adding the isolation guarantee. While it redundantly restates the default value already in the schema, it adds semantic meaning that the schema lacks.

  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 starts with a specific verb and resource: 'Delete ALL memories for a user.' It clearly distinguishes itself from sibling tools like 'remember', 'recall', and 'forget' by emphasizing the bulk, all-encompassing scope ('ALL'). The purpose is 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 clear context: it is a destructive, bulk delete operation scoped to a user namespace, with a default namespace. However, it does not explicitly name alternatives or state when not to use it (e.g., 'use forget for individual memories'). The usage is clear but lacks explicit exclusions.

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

• forgetA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden, and it does well. It explicitly labels the operation as 'Destructive', describes the matching and removal process, and states the no-op behavior when no match exists. This fully discloses safety-critical aspects.

  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 well-structured: a headline, a warning/behavior line, and an Args list. Every sentence adds value, and there is 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?

  The description covers the tool's purpose, destructive nature, edge case (no-match), and parameter meanings. Since an output schema exists, return values need not be described. For a two-parameter tool, this is complete.

  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 description coverage is 0%, but the 'Args' section provides meaningful semantics: query is described as 'Describes the memory to remove' and user_id as 'Namespace to delete from (default "default")'. This goes beyond the schema's minimal labels and fully compensates for the lack of 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 uses a specific verb ('Delete') and resource ('memory') with explicit scope ('single memory most relevant to query'). It clearly distinguishes this from reset_memories (bulk deletion) and remember/recall (memory creation/retrieval).

  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 conveys clear context: this is for deleting a single memory based on relevance to a query. It implies the distinction from bulk deletion via the word 'single' but does not explicitly name alternatives or provide when-not-to-use guidance. This is a clear context, no exclusions, so a 4 is appropriate.

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