Server Quality Checklist

Tool Scores

• call_agent_asyncA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It clearly discloses the NON-BLOCKING behavior, immediate return of task_id, and the necessity of later calling get_agent_result. It also demonstrates parallel usage. It does not cover failure modes or error handling, but the core behavioral traits are well addressed.

  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 sections (Workflow, Why async is better, Parallel search pattern) and front-loads the key behavior. It is slightly longer than necessary, but each section contributes to understanding the tool's usage pattern.

  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 an async launch tool without an output schema, the description is remarkably complete. It covers the return value (task_id), the full workflow including how to retrieve results with get_agent_result, and demonstrates a parallel search pattern. It integrates well with sibling tools and addresses the uncertainty of async behavior.

  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 already provides 100% coverage with descriptions for all four parameters (agent, prompt, cwd, context). The description adds a usage example mapping agent and prompt to positional arguments, but does not enrich the meaning of cwd or context beyond the 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 clearly states the tool starts an agent task in the background (NON-BLOCKING) and returns a task_id immediately. This specific verb+resource+behavior distinguishes it from siblings like call_agent (likely synchronous) and aligns with get_agent_result for retrieval.

  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 a clear workflow (start task, continue work, retrieve result with get_agent_result) and explains why async is better for parallel searches. It recommends this tool for explore/researcher use cases, but does not explicitly state when NOT to use it (e.g., when immediate results are needed versus call_agent).

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

• get_agent_resultA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden and does well by explaining the block parameter, timeout default, and return of 'task status and result if completed'. It does not cover edge cases like timeout behavior or errors, but provides solid behavioral guidance for a simple polling tool.

  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 extremely concise, front-loading the purpose, then listing parameters with defaults in a clear structure, and ending with return behavior. Every sentence earns its place with no redundant 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 async result retrieval tool with only 3 parameters and no output schema, the description covers the essential aspects: purpose, parameters, blocking behavior, and return value. It lacks explicit error-handling details but is otherwise complete for the tool's simplicity.

  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 100%, so the baseline is 3. The description repeats parameter information already in the schema (e.g., task_id from call_agent_async, block default false) without adding new semantic meaning beyond what the schema provides.

  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 'Get result from async agent task' uses a specific verb and resource, clearly distinguishing it from sibling tools that initiate agent calls. It explicitly references call_agent_async, establishing the relationship and making the tool's purpose unambiguous.

  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 implies usage after call_agent_async by requiring a task_id from that tool, which provides clear context. It does not explicitly state when not to use it (e.g., for sync calls), but the async-specific wording and companion sibling names make the intended use evident.

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

• call_agents_batchA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden. It fully discloses blocking behavior, parallel execution, and the risk of waiting for the slowest agent. It doesn't cover failure modes or return details, but core behavioral traits are clearly communicated.

  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 longer than ideal but well-structured with headings and examples. The warning section is impactful, and the examples illustrate misuse and correct use. However, it could be tightened without losing value.

  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 tool with no output schema, the description explains blocking semantics, parallel execution, and appropriate use cases. It doesn't describe the return value format or how to retrieve individual results (though sibling get_agent_result exists), which keeps it from being fully complete.

  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?

  Input schema describes both cwd and calls with 100% coverage, so the baseline is 3. The description's example adds a concrete JSON structure showing the calls array shape, but doesn't explain parameters beyond the schema. Reasonable but not exceptional.

  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 clear verb+resource statement: 'Execute multiple agents in PARALLEL (BLOCKING until ALL complete).' It explicitly distinguishes itself from call_agent_async, making its purpose unambiguous.

  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 advises against typical use, names the preferred alternative (call_agent_async × N), and lists precise conditions where batch is appropriate. This is outstanding when-to-use guidance.

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

• call_agentA
  4.5/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the full burden. It discloses that the call is blocking, takes 30-120s, and that advisor is read-only. However, it does not describe the return value shape, error behavior, or whether the agent can mutate files, which limits full transparency.

  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 front-loaded with the key blocking behavior and then uses headers, a decision tree, and a table for efficient scanning. It is somewhat long, but most content earns its place by directly informing tool selection; the 'Why async for search agents?' section is slightly redundant with the decision tree.

  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 there is no output schema and no annotations, the description does substantial work by covering routing, agent roles, and timing expectations. It lacks an explicit statement of the return value or post-call behavior, which would make it fully complete. Overall, it is highly informative but has a notable gap.

  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 coverage is 100%, so the baseline is 3. The description adds significant semantic value by detailing each agent's role and pairing them with the appropriate call mode. It does not enrich prompt/context/images beyond the schema, but the agent-level detail meaningfully helps invocation.

  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 'Synchronous single agent call (BLOCKING, 30-120s)', which precisely names the action, resource, and blocking behavior. It clearly distinguishes from async siblings by stating what this tool is used for versus call_agent_async, and the mapping table reinforces the exact agent-to-tool pairing.

  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 decision tree provides explicit when-to-use and when-not-to-use guidance, including 'NEVER this tool' for explore/researcher and alternatives like call_agent_async and call_agents_batch. The Agent → Tool Mapping table further clarifies which agents should use this tool synchronously.

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