Server Quality Checklist

Tool Scores

• expand_aroundC
  2.4/5.0
  Behavior2/5

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

  Without annotations, the description must fully disclose behavior. It only states the action and result type, but omits side effects, safety profile, permissions, or what qualifies as a 'turn'. The term 'raw' is vague.

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

  Conciseness3/5

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

  The description is a single sentence, which is concise but overly terse. It could include essential parameter relationships without becoming lengthy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's complexity (4 parameters, required uuid and session_id) and lack of annotations, the description is insufficient. The output schema may partially compensate, but the description should explain the anchor concept more clearly.

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

  Parameters1/5

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

  The description does not explain any parameters (uuid, session_id, after, before). With 0% schema description coverage, the agent receives no semantic help beyond parameter names and types.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly specifies the tool returns raw turns around an anchor, listing the content types (tool calls, outputs, thinking). It distinguishes the tool's purpose from siblings like grep or recall_search, though it could explicitly contrast them.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

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

  No guidance is provided on when to use this tool versus alternatives (e.g., grep for searching turns, step for navigation). The description lacks contextual hints for triggering conditions.

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

• stepC
  2.4/5.0
  Behavior2/5

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

  With no annotations, the description is the sole source of behavioral info. It only mentions the basic action without discussing side effects, permissions, rate limits, or the effect of the 'count' parameter. The tool's behavior beyond a single step is opaque.

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

  Conciseness3/5

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

  The description is very short (one sentence), which is concise but does not front-load critical parameter info. It could be equally concise yet more informative by adding parameter hints.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given 4 parameters (3 required) and an output schema, the description is insufficient. It does not explain how sessions, UUIDs, or counts relate to walking, nor what the tool returns. This makes it hard for an AI agent to use correctly without additional context.

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

  Parameters1/5

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

  Schema coverage is 0%, so the description must compensate, but it only mentions 'direction' ('next' or 'prev'). It does not explain 'uuid', 'session_id', or 'count' (with default 1). Users are left guessing the meaning and purpose of these parameters.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the verb 'Walk' and the resource 'adjacent turn', with acceptable direction values 'next' or 'prev'. It is specific enough to distinguish from sibling tools like expand_around, grep, recall_search, recent_sessions, which are not navigation-focused.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

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

  No guidance is provided on when to use this tool versus alternatives, or any prerequisites. The description lacks context on when stepping makes sense or when other tools might be more appropriate.

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

• grepB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so description must fully disclose behavior. It indicates a non-destructive read operation but lacks details on permissions, rate limits, performance, or what happens on missing indices. The mention of 'raw session transcripts' gives data source context but is minimal.

  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?

  Two sentences with purpose and usage guidance front-loaded. No wasted words, but could be slightly more structured (e.g., separate lines for parameters).

  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 3 parameters, no annotations, and an output schema (not shown), the description covers the main goal and one parameter's usage. Missing details on pattern format and session_id, as well as behavioral aspects. Sufficient for a simple scan but not comprehensive.

  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 0%, so description must compensate. It explains scope_cwd (how to restrict scanning) but does not describe pattern (required) or session_id. Pattern being a substring vs regex is ambiguous, and session_id's purpose is unclear.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description clearly states the tool performs an on-demand substring scan over raw session transcripts, which is specific and distinct from sibling tools like recall_search (likely semantic) and expand_around. However, it does not explicitly differentiate from siblings.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

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

  Provides guidance on when to use scope_cwd (restrict to project vs global scan), but no explicit guidance on when to use this tool versus alternatives, nor when not to use it.

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

• recall_searchA
  3.5/5.0
  Behavior3/5

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

  No annotations provided, so description carries behavioral burden. It discloses semantic search and ranking, but does not mention read-only nature, side effects, permissions, or rate limits. 'Anchors' are not defined, leaving some ambiguity.

  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?

  The description is concise with two sentences: one for purpose and one for parameter explanation. No redundant words. However, it lacks parameter details which would improve structure without adding much length.

  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 3 parameters and an output schema, the description covers purpose and one parameter well. However, missing explanations for 'query' and 'k' make it incomplete. The output schema existence partially mitigates need for return value details.

  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 description must add meaning. Only scope_cwd is explained in detail; query and k parameters have no semantic description. k likely controls number of results but is not stated. This leaves significant gaps for agent 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?

  The description uses specific verb 'semantically search' and resource 'past Claude Code sessions', with clear output 'ranked anchors'. It distinguishes from siblings like grep (text search) and recent_sessions (list) by focusing on semantic search across sessions.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

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

  The description explains when to use scope_cwd (restrict to project) versus omit (global), but lacks explicit guidance on when to use recall_search over siblings like grep or step. No when-not-to-use or alternative suggestions.

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

• recent_sessionsA
  4.7/5.0
  Behavior5/5

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

  No annotations provided, so description fully discloses behavior: lists sessions sorted by freshness, includes fields, and explains scope_cwd parameter effect. No contradictions or hidden traits.

  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: starts with main purpose, then provides usage details. Slightly verbose but each sentence adds value. Could be condensed slightly.

  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?

  Output schema exists, and description already explains return fields (session_id, project, turns, last_activity, etc.). Complete for a list tool with good parameter explanations.

  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 description adds meaning: explains default limit (10) and scope_cwd usage (restrict to current directory). Provides semantic context 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?

  Description clearly states it lists most recently active sessions, freshest first. Verb 'list' and resource 'recent sessions' are specific. Distinguishes from siblings by describing its unique purpose: surfacing session arcs across thread splits.

  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?

  Describes when to use: to see current state of work, freshness, and reassemble thread arcs. Does not explicitly mention when not to use or alternatives, 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.