Server Quality Checklist

Tool Scores

• list_sessionsA
  3.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden for behavioral transparency. It discloses the sorting order and pagination behavior, but does not mention whether the operation is read-only, potential side effects, or error handling. It is adequate but not comprehensive.

  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, with a one-sentence purpose followed by a clear parameter list. Every line serves a purpose, and there is no redundant or unclear text.

  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?

  For a simple list operation, the description covers the purpose, ordering, and all parameters. The output schema documents return values. It lacks explicit mention of edge cases or when to use alternatives, but it is sufficiently complete for 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 provides no parameter descriptions (0% coverage), but the description compensates fully by explaining each parameter's meaning: project slug filtering, limit for max results, and offset for pagination. It adds clear value beyond the schema's types and defaults.

  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 'List sessions for a project, sorted by most recent first' with a specific verb and resource, and it distinguishes from sibling tools like list_projects by focusing on sessions. It could be more explicit about how sessions are defined, but the core purpose is clear.

  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 implies usage for listing sessions but does not explicitly state when to use this tool over alternatives like search or get_thread. There is no mention of exclusions or conditionals, making the usage guidance implicit rather than explicit.

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

• get_threadA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses useful behaviors: 'Only includes user and assistant messages', 'Supports pagination for long threads', and explains the include_tool_calls option. However, it does not explicitly state read-only safety, error handling, or whether messages are returned in chronological order (though 'root-to-leaf path' implies structural order).

  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 well-structured with a front-loaded purpose, followed by behavioral notes and a clearly formatted Args list. It is appropriately sized given the need to document 6 parameters, and every sentence contributes value 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?

  The description covers the tool's core function, filtering behavior, pagination, and parameter semantics. Given an output schema exists (so return format is handled) and no annotations are provided, it includes enough context for an agent to select and invoke the tool, though it could add a note about sorting order or error cases.

  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 description's Args section thoroughly explains every parameter with added meaning: limit has 'max 200', offset is 'Skip first N messages', leaf_uuid 'Empty for the primary (latest) thread', session_id 'UUID (or prefix)', project 'Optional project slug', and include_tool_calls 'Show tool names used in assistant messages'.

  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 'Get a conversation thread (root-to-leaf path through the tree)', providing a specific verb, resource, and scope. It distinguishes itself from sibling tools like get_tree (which likely returns the entire tree) by emphasizing 'root-to-leaf path' and 'Only includes user and assistant messages'.

  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 implies usage for retrieving a single conversation thread, with details like 'leaf_uuid empty for the primary (latest) thread'. However, it does not explicitly compare against alternatives such as get_tree or get_forks, or state when to prefer this tool over them.

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

• get_forksA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden. It explains that fork points represent branchings from retries/edits and identifies primary vs. abandoned branches. However, it does not disclose potential side effects, required permissions, or output structure, though the tool appears read-only by name.

  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, front-loaded with the main purpose, and includes a clear Args section. Every sentence serves a purpose without excessive verbosity.

  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, return value descriptions are unnecessary. The tool's purpose, branch behavior, and parameter roles are sufficiently described. Slight gap: no usage guidance relative to siblings, but that is covered under the usage dimension.

  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 has 0% description coverage, but the description provides meaningful explanations for all three parameters: session_id (UUID or prefix), project (optional slug), and fork_uuid (specific fork point or all). This fully compensates for the schema's lack of 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 'Get fork points in a session with diverging branch details' with a specific verb and resource. It distinguishes from siblings by focusing on branch/fork history rather than session lists, trees, or threads.

  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?

  Describes what the tool does and shows branch details, implying use when fork information is needed, but does not explicitly state when it should be used over alternatives or when to avoid it. No exclusion criteria or comparison to sibling tools like get_thread or get_tree.

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

• list_projectsA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of disclosing behavior. It adds useful context (only projects with session history, return fields) beyond the tool name. However, it does not explicitly state that the operation is read-only, nor does it mention any potential limitations (e.g., pagination, permissions), which would be more important for tools with side effects. For a simple list, this is acceptable but not exhaustive.

  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, front-loaded with the primary action, and includes only relevant details about return values. No filler or redundant phrases.

  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 simple with no parameters and an output schema. The description explains what the tool returns and its filtering condition, which is complete for this level of complexity. The existence of an output schema covers detailed return structure, so the description doesn't need to enumerate every field.

  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 tool has zero parameters, so the schema already fully covers the inputs. The description adds nothing about parameters, but there is nothing to add. Per the rubric, a baseline of 4 applies for zero-parameter tools.

  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 begins with a specific verb ('List'), resource ('Claude Code projects'), and scope ('that have session history'). It also enumerates the return fields (slugs, session counts, total size), clearly distinguishing it from sibling tools like list_sessions or get_tree, which operate at different levels.

  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 by specifying it lists projects with session history, which implicitly tells the agent when to use it (project-level overview). However, it does not explicitly mention alternatives or exclusions, so it falls short of a 5. The context is clear enough that no other tool would be mistaken for this one.

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

• searchA
  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 case-insensitive substring matching, fork awareness, max result limits, optional subagent inclusion, and the return of surrounding conversational context and branch info. While it does not explicitly state read-only behavior, it is evident from 'search' that no side effects occur.

  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: a one-line purpose, a sentence on scope/return value, and a clear Args list. No filler or repetition. It is front-loaded with the most important information and every sentence adds value.

  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 moderately complex with four parameters and an output schema. The description covers search scope, return format, fork awareness, parameter behavior, and constraints (max 50 results). Since an output schema exists, not detailing return fields is appropriate. This is complete enough for an agent to invoke correctly.

  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 no property descriptions, but the description's Args section explains every parameter: query (search text, case-insensitive), project (filter, empty for all), max_results (default 10, max 50), and include_subagents (search subagent files). This fully compensates for the 0% schema coverage.

  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 opening sentence 'Full-text search across Claude Code session history' uses a specific verb (search) plus a clear resource (session history), and the description clarifies that it searches conversation text with fork awareness and returns context/branch info. This clearly distinguishes it from sibling tools that list projects/sessions or retrieve threads/trees.

  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: this is the tool for searching text across sessions, with optional filtering by project and subagents. It does not explicitly mention alternatives or when not to use it, but the context is unambiguous enough that an agent would use it for free-text search rather than listing or retrieval tasks.

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

• get_treeA
  4.8/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden. It discloses meaningful behavioral details: the tool returns a tree with fork points, branch summaries, compaction boundaries, and leaf nodes, and session_id accepts a UUID or prefix. While it does not explicitly state it is read-only, the 'get' verb and structural focus strongly imply a safe, non-mutating operation.

  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. It leads with a clear purpose sentence, adds relevant details, includes usage guidance, and lists parameters in a clean format. Every sentence earns its place with no redundant content.

  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 moderate complexity (2 parameters, no enums) and the presence of an output schema, the description is complete. It explains what the tool shows, when to use it, and clarifies each parameter. The mention of 'before navigating with get_thread or get_forks' provides necessary context within the sibling toolset, and the output schema presumably covers return value structure.

  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 has no descriptions (0% coverage), but the description fully explains both parameters: 'session_id: Session UUID (or prefix)' and 'project: Optional project slug to narrow lookup.' This adds crucial format and purpose information beyond the schema, compensating entirely 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 the tool's purpose with a specific verb and resource: 'Get the conversation tree structure for a session.' It further distinguishes itself from sibling tools by listing what it shows (fork points, branch summaries, compaction boundaries, leaf nodes) and explicitly references get_thread and get_forks as navigation tools.

  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?

  Provides explicit usage guidance: 'Use this to understand the structure before navigating with get_thread or get_forks.' This states when to use (before navigating) and names the alternative tools, making the decision boundary clear.

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