Server Quality Checklist

Tool Scores

• nexus.memory_createA
  3.7/5.0
  Behavior2/5

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

  No annotations provided, so description must carry full behavioral burden. It only mentions persistence (a write operation) but lacks details on side effects, authentication, rate limits, or content restrictions beyond metadata constraints.

  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, front-loaded with the core action. No unnecessary words; every sentence adds value.

  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 core purpose and key parameters adequately, but lacks details on content length limits, valid_until semantics, and expected return values despite output schema existence.

  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 29%, meaning most parameters lack descriptions. The description adds value for memory_type (episodic/semantic/procedural mapping) and metadata (free-form tags), but does not elaborate on user_id, content, valid_until, or agent_id.

  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 explicitly states 'Persist a new memory' and provides concrete usage scenarios (e.g., storing preferences, facts, code snippets). It distinguishes from siblings (retrieve, feedback, search) by focusing on creation.

  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 guidance on when to use (e.g., 'when user explicitly asks to remember X') and maps memory_type to use cases. It does not explicitly exclude other scenarios, but the sibling list implies alternatives.

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

• nexus.memory_searchA
  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 full burden. It discloses the Chinese fallback behavior for hybrid mode, but omits other behavioral traits like read-only nature, authorization needs, or result characteristics.

  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, front-loaded with key purpose and usage context; no wasted words.

  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?

  With 6 parameters, no annotations, and an output schema, the description provides minimal behavioral and parameter guidance. It covers usage context but lacks details on parameter effects and output semantics, making it barely adequate for correct tool invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is only 17% (only 'mode' has description). The description adds some context for 'mode' (Chinese fallback) but does not clarify other parameters like memory_type, score_threshold, or limit beyond schema basics.

  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 it performs targeted semantic search over memories, differentiating from siblings by specifying it is for specific keyword/topic queries without needing conversation/knowledge layers.

  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 guidance ('when query has specific keyword/topic and user wants list of memories (no need for conversation/knowledge layers)') but does not explicitly name alternative tools or state when not to use.

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

• nexus.memory_feedbackA
  4/5.0
  Behavior3/5

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

  With no annotations, description carries burden. It discloses that user_id is internal and not forwarded, and that feedback drives quality_score reranking. Missing side effects, idempotency, 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?

  Two sentences, front-loaded with action, no fluff. Efficiently conveys core purpose and usage.

  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?

  Covers key aspects: purpose, input requirements, per-memory feedback, and feedback loop impact. Lacks explanation of output schema, but that is acceptable since an output schema exists.

  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 high (83%); description adds marginal value by explaining user_id's internal nature and item_feedback's structure, but largely repeats 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?

  Description clearly states this tool submits per-memory feedback on a previous nexus.context_retrieve call, specifying key parameters (retrieve_id, rating, useful flag). It distinguishes from siblings (retrieve, create, search) by focusing on feedback.

  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 instructs to pass retrieve_id from earlier output, implying usage after retrieval. Does not list exclusions or alternatives, but context is clear given sibling tools.

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

• nexus.context_retrieveA
  4.2/5.0
  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 that a single call returns multiple data types and gives specific behavioral guidance for the 'as_of' parameter, including the restriction against inferring time context from conversation. This adds valuable transparency beyond the schema.

  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: three sentences that convey the purpose, usage guideline, and a key behavioral note. Every sentence earns its place 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 the existence of an output schema (not shown but indicated), the description appropriately avoids explaining return values. It covers the key combination of data types and the critical 'as_of' constraint. Minor gap: no mention of error conditions or performance, but overall sufficient for a retrieval tool.

  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 50%, so the description should compensate. It adds meaningful detail for the 'as_of' parameter (e.g., max 90 days, no inference from context), but does not elaborate on user_id, query, or limit beyond what the schema provides. This meets the baseline but does not elevate.

  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: retrieving context from prior sessions, conversations, or stored facts. It specifies that it returns 'memories, recent conversation turns, and knowledge entities together,' and distinguishes from sibling nexus.memory_search by stating 'Prefer this over nexus.memory_search when query is open-ended.'

  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 a clear condition for use ('when user asks anything that might need context from prior sessions...') and suggests an alternative for more specific queries (nexus.memory_search). However, it does not explicitly list when not to use this tool or other exclusions.

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