Server Quality Checklist

Tool Scores

• claude_code_modelsA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, which sets the safety baseline. The description adds useful context: the tool operates against the 'authenticated Claude Code CLI', returns specific data elements (identifiers, resolved models, descriptions, supported effort/mode), and explicitly states it does not run an inference turn. This goes beyond the annotations without contradicting them.

  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, with the first sentence stating action and scope, and the second summarizing the return content. It is front-loaded with the verb and resource, and every word contributes value without fluff.

  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, rich annotations, and presence of an output schema, the description is largely complete: it explains what the tool does, its auth context, and what it returns. It slightly lacks explicit guidance on when to prefer this over run/resume, but that is a minor gap and the 'without running' phrase partially covers it.

  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?

  The input schema provides descriptions for all four parameters, giving 100% coverage. The description does not add extra meaning about parameters such as cwd or timeoutMs, but since the schema already handles this, the baseline of 3 is appropriate.

  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 a specific verb 'List' and clearly identifies the resource: 'models available to the authenticated Claude Code CLI'. It also distinguishes itself from sibling tools by adding 'without running a model inference turn', making it unmistakably a discovery tool rather than an execution tool.

  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: use this tool to list models without triggering inference. However, it does not explicitly mention sibling tools (claude_code_run, claude_code_resume) or state 'use X instead for running models', so it stops short of full exclusion guidance.

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

• claude_code_resumeA
  4.2/5.0
  Behavior4/5

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

  The annotation already flags destructiveHint=true and readOnlyHint=false, and the description adds the critical behavioral trait that the call blocks until the turn completes. It also adds the 'Do not poll' directive, which is extra guidance not inferable from 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 two short, front-loaded sentences with no filler. Every word contributes to the core understanding.

  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 complex tool with 16 parameters, the description covers the essential blocking/session-resume behavior and the no-poll rule. Since an output schema exists and annotations cover the safety profile, the description is adequately complete, though a bit terse given the parameter count.

  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 81%, so the schema already documents most parameters in detail. The description itself adds no parameter-level semantics, but the baseline of 3 is appropriate given the high 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 description uses a specific action ('Resume') and resource ('persisted Claude Code session'), adding a key distinguishing behavior (keeping the MCP call open until completion). This clearly differentiates it from sibling tools like claude_code_run (new sessions) and claude_code_models (listing models).

  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 for using this tool (resume persisted session) and explicitly instructs 'Do not poll,' which is useful operational guidance. However, it doesn't explicitly state when not to use it or name alternatives, so it stops short of full exclusion guidance.

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

• claude_code_runA
  4.2/5.0
  Behavior4/5

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

  The description adds significant behavioral context beyond annotations: the call blocks until completion and should not be polled. Annotations already indicate destructive/open-world behavior, but the description enriches the operational understanding with the blocking and delegation guidance. No contradiction with 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?

  Three concise sentences: the first states the core purpose, the second gives a direct operational instruction, and the third provides a delegation note. Every sentence earns its place, with no redundancy or fluff.

  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 (15 parameters, long-running, destructive), the description captures the critical orchestration behavior (blocking, no polling, delegation) and benefits from a rich output schema. It doesn't mention preconditions or resume alternatives, but overall it provides sufficient context for an agent to invoke 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 description coverage is 80%, so parameters are largely self-documenting. The description does not add parameter-level meaning; it focuses on behavior. With high schema coverage, a score of 3 is appropriate—no additional value provided beyond what the schema already does.

  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 'Run a new Claude Code session and keep this single MCP call open until it completes.' This clearly identifies the action, resource, and blocking behavior, and distinguishes from the sibling 'claude_code_resume' by emphasizing 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 Guidelines4/5

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

  It provides clear operational guidance: 'Do not poll' and explicit delegation advice for long tasks. While it doesn't explicitly mention using 'claude_code_resume' for existing sessions, the phrase 'new session' implies the distinction. Overall, it gives useful context for when and how to use the tool.

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