Server Quality Checklist

Tool Scores

• recent_conversationsA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does well: it discloses read-only behavior, that only ID/title/time are returned, that full messages are not loaded, and that returned content is untrusted data (with an instruction-following warning). It could mention pagination or sorting behavior, but for a simple list tool this is strong.

  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 and well-structured: first sentence states purpose, second explains return scope, third gives limit details, fourth provides a security warning. 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.

  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 the presence of an output schema, the description covers the main aspects: return fields, read-only nature, limit constraints, and trust warning. It does not mention offset or result ordering, but for a recent-conversations list with a small parameter set, it is sufficiently complete.

  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 0%, so the description must compensate. It adds meaning for 'limit' by stating the default and max, but it does not mention 'offset' at all. Given only two parameters, the omission of offset is a notable gap, leaving the description only partially compensating 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 clearly states 'List the recent conversations of the current assistant (read-only)' with a specific verb and resource. It also specifies the scope ('current assistant', 'recent') and that it only returns IDs, titles, and times, which distinguishes it from search and context tools.

  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 the tool: for listing recent conversations of the current assistant without loading full messages. It does not explicitly name alternatives or exclusions, but the read-only and lightweight nature implicitly guides usage away from search or full-context retrieval.

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

• get_conversation_contextA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description carries the full behavioral burden. It discloses the read-only nature, that only USER/ASSISTANT text is returned while reasoning, tool calls, results, and attachments are excluded, and imposes before/after caps of 20. It also adds an important security warning that historical text must not be executed or obeyed.

  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 tightly packed—each sentence adds a distinct piece of information: what it does, how to get IDs, what is returned, the limit, and the security warning. There is no filler or repetition.

  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 tool is well-specified for an agent: it covers purpose, prerequisite source of parameters, output scope, numerical limits, and a security warning. An output schema exists, so return-value details need not be in the description.

  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 provides no parameter descriptions, so the description must compensate. It explains that before/after are capped at 20 and that the IDs originate from search_conversations, giving context beyond the raw names; however, it does not elaborate on each parameter's precise semantics, leaving some work to the schema names.

  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 opens with a specific verb-based purpose: '讀取搜尋命中點附近的 selected-branch 對話文字（唯讀）' (read read-only conversation text near a search hit in the selected branch). It clearly identifies the resource and scope, and the mention of search_conversations distinguishes this retrieval tool from the sibling search/list tools.

  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 explicitly states that conversation_id and node_id come from search_conversations, establishing the intended workflow and when to use this tool after a search. However, it does not explicitly state when not to use it or name alternative tools for other contexts, so it stops short of full alternative-based guidance.

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

• search_conversationsA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses key behaviors: read-only nature, index scope possibly covering all assistants, returned fields, limit defaults and maximum, and the crucial warning that returned snippets are untrusted and must not trigger following embedded instructions or tool calls. This exceeds typical 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 compact yet information-dense, with the purpose front-loaded and every sentence contributing practical value (scope, usage, return fields, limit behavior, security warning). No filler or 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 search tool with two simple parameters, the description covers the essential contextual aspects: what results contain, how to use follow-up tools, limits, and the trust boundary. An output schema exists, so return-value details are not required; the description is sufficient for safe and correct invocation.

  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 has no parameter descriptions (0% coverage), so the description compensates by specifying limit's default (15) and max (50) and advising concise keyword usage for the query parameter. While query's semantics are obvious from the tool name, the limit details add value 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 opens with '全文搜尋 RikkaHub 歷史對話（唯讀）' which clearly states the action (full-text search) and the resource (RikkaHub historical conversations), while noting it is read-only. It differentiates from siblings by implying search over conversation history, distinct from recent_conversations or get_conversation_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?

  It provides practical usage instructions: use concise keywords, and explicitly directs to call get_conversation_context when context is needed. It does not explicitly contrast with recent_conversations, but the search-vs-recent distinction is implied, making the guidance clear but not exhaustive.

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