Server Quality Checklist

Tool Scores

• claude_code_sessionB
  3.1/5.0
  Behavior3/5

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

  Annotations provide destructiveHint: true, indicating destructive actions. The description mentions cancel and interrupt, but does not clarify differences or side effects. With annotations, the description adds no extra behavioral context.

  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?

  Very concise single sentence, front-loaded with verbs. Could be structured better for multi-action tools, but not verbose.

  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 multiple actions and an output schema, the description should detail what each action does and prerequisites (e.g., sessionId required for get/cancel/interrupt). Missing these details makes it incomplete for a complex 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 100%; parameters are well-documented in the schema. The description adds no additional meaning beyond what the schema provides. Baseline 3 is appropriate.

  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 tool manages sessions with actions like list, inspect, cancel, or interrupt. It distinguishes from sibling tools like 'claude_code_check' or 'claude_code_reply' which focus on other aspects.

  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 on when to use this tool vs siblings, or when to choose one action over another. For a tool with multiple distinct actions, such guidance is missing.

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

• claude_code_checkA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds valuable behavioral context: explains token-wasting risks, the need for adaptive polling, and the ability to interrupt sessions via the interrupt parameter. It does not contradict annotations.

  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 clear headings for polling frequency and main loop. It is somewhat lengthy but every sentence adds essential context, especially given the tool's complexity. Could be slightly more concise, but overall efficient.

  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 complexity (11 parameters, nested objects, output schema exists), the description covers the high-level flow, polling states, and main loop adequately. It does not explain all edge cases, but schema descriptions handle parameter details. Completeness is strong.

  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 100%, with each parameter already explained. The description adds semantic value by explaining how parameters like action, cursor, and decision fit into the polling loop and permission response flow, going beyond the schema's individual 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 polls session state or answers pending permission requests, with a specific verb+resource. It distinguishes from siblings (claude_code, claude_code_reply, claude_code_session) by its unique polling and permission-responding functionality.

  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 polling frequency guidelines based on session state, including minimum intervals and when to stop polling. Also describes the main loop pattern and adapts intervals based on task complexity. This exceeds typical usage guidance.

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

• claude_codeA
  4.6/5.0
  Behavior5/5

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

  Beyond the annotations (destructiveHint=true, openWorldHint=true), the description adds critical behavioral context: the tool starts a background process, explains the long-running nature (10+ minutes), details the polling loop, permission handling, and internal tool behavior. It also clarifies that allowedTools is not a strict allowlist unless strictAllowedTools is true, providing transparency on permission control.

  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 appropriately sized for the complexity, front-loading the core purpose and polling loop. It then covers permissions, continuation, and internal tool lists in a structured manner. While long, every section adds value; could be slightly more concise but earns a 4 for effective structure.

  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 complexity (asynchronous polling, permissions, internal tools) and the presence of a detailed schema and output schema, the description is complete. It covers the main loop, permission handling, session management, runtime tool discovery, and permission control nuances, leaving no significant gaps for an agent to use the tool correctly.

  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 100%, so the baseline is 3. The description adds minimal parameter insight beyond the schema: it reiterates that prompt starts a run and mentions storing nextCursor from polls, but does not elaborate on other parameters. The description focuses on the workflow rather than individual parameter details, which is acceptable given the schema's thoroughness.

  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 starts a background Claude Code run and returns a sessionId immediately, with no final result returned here. It distinguishes itself from sibling tools (claude_code_check, claude_code_reply, claude_code_session) by explaining when to use each and that claude_code_reply should be used for continuation instead of starting a new session.

  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?

  The description provides explicit guidance on when to use this tool: to start a run. It details the main polling loop using claude_code_check, handling permission requests with respond_permission, adjusting polling cadence based on progress, and waiting for long-running work. It also tells when to use claude_code_reply instead of starting a new session.

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

• claude_code_replyA
  4.9/5.0
  Behavior5/5

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

  The description discloses that the tool returns immediately and requires polling, adds nuance about diskResumeConfig, and aligns with annotations (destructiveHint=true, openWorldHint=true). It provides valuable behavioral context beyond the annotations.

  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 (3 sentences), front-loaded with purpose, and each sentence adds unique value. No redundancy or wasted words.

  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 presence of an output schema and full parameter coverage, the description sufficiently covers essential behavioral aspects and use cases. It is complete for an async tool with polling and conditional disk resume.

  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?

  With 100% schema description coverage, the baseline is 3. The description adds meaning by clarifying when to use sessionId and diskResumeConfig, exceeding the schema's documentation.

  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 sends a follow-up to an existing session, distinguishes it from starting a new session via 'claude_code', and references polling via 'claude_code_check'. It explicitly mentions reusing sessionId, making the verb and resource specific.

  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?

  The description explicitly says to reuse sessionId instead of starting a new session, advises polling with claude_code_check, and specifies when to use diskResumeConfig. It provides clear context and exclusions for usage.

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