Server Quality Checklist

Tool Scores

• subagent_closeB
  3/5.0
  Behavior2/5

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

  With no annotations, the description must fully disclose behavior. It only states 'release runtime state' but omits side effects, mutability, or whether the action is reversible.

  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 a single concise sentence with no waste, though it could afford a few more words for clarity without losing conciseness.

  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?

  Despite having an output schema, the description fails to address parameter usage or any contextual details, making it incomplete for a tool with no annotations.

  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%, and the description does not mention the required parameter 'target' or hint at its meaning, leaving the agent without guidance.

  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 'Close' and identifies the resource 'Open Subagent MCP run', clearly distinguishing it from sibling tools like subagent_spawn (create) or subagent_rollback (undo).

  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 (closing an open run) but provides no explicit guidance on when to use it versus alternatives, nor any conditions or prerequisites.

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

• subagent_waitA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description carries full burden. It discloses that results include status, summaries, changed_files, etc., for audit purposes, but it does not explain blocking behavior, timeout handling, or error states. The timeout parameter is not mentioned.

  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 consists of two concise, front-loaded sentences. The first states the purpose, the second details the output. No extraneous information.

  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 (waiting for subagents with a timeout), the description lacks completeness. It does not address error conditions, partial results, or how to interpret outputs like 'status'. The timeout parameter is undocumented.

  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?

  The input schema has 2 parameters (targets, timeout_ms) with 0% description coverage. The description does not define what 'targets' refers to (e.g., subagent IDs) or explain the timeout parameter. It adds no semantic value beyond the schema property names.

  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 verb 'Wait' and the resource 'one or more Open Subagent MCP runs'. This directly distinguishes it from sibling tools like subagent_spawn, subagent_close, subagent_rollback, and subagent_send_message, each of which has a different action.

  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 after spawning subagents, but it does not explicitly state when to use this tool versus its siblings. There is no guidance on prerequisites or 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.

• subagent_send_messageA
  3.6/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It discloses a key behavioral trait: each follow-up creates a new rollback segment. This adds value beyond just stating the purpose. However, other aspects like idempotency, error handling, or permissions are absent.

  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?

  Two sentences, front-loaded with the purpose, and no unnecessary words. Every sentence earns its place by conveying essential information.

  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?

  Despite having an output schema, the description omits parameter guidance and usage alternatives. For a tool with 4 parameters and no annotations, the description provides only the rollback context, leaving gaps in understanding how to use each parameter effectively.

  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 description coverage is 0% and the tool has 4 parameters (target, message, items, interrupt). The description fails to explain any of these parameters, only mentioning segment_id which is not a parameter of this tool. The description does not compensate for the missing 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 sends a follow-up message to an existing subagent run. The verb 'send' and resource 'follow-up message' are specific and distinguish it from siblings like spawn, close, rollback, or wait.

  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 how to use segment_id with subagent_rollback for undo, but does not provide explicit guidance on when to use this tool versus alternatives. It implies usage for follow-up messages, but lacks when-not scenarios or comparative context.

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

• subagent_spawnA
  3.9/5.0
  Behavior4/5

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

  No annotations present, so description carries full burden. It discloses that only files under cwd are accessible, external paths must be declared and pass security checks, and that long timeouts need explicit authorization. This adds behavioral context beyond the basic 'start a run'.

  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?

  Description is a single paragraph of three sentences with no wasted words. It front-loads the purpose and then adds important behavioral details. Could benefit from slight structuring (e.g., bullet points for parameters) but overall efficient.

  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?

  The description covers key aspects like agent type, timeout, and external paths, but leaves many parameters (items, fork_context, dry_run, max_steps) undefined. With 11 parameters and no annotations, the description is incomplete for full autonomous selection. Output schema exists but doesn't compensate for missing parameter semantics.

  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%, yet the description only clarifies agent_type, timeout_seconds, allowed_external_roots, and explicit_authorizations. Parameters like items, fork_context, dry_run, max_steps are left unexplained. Given the high parameter count, more parameter-level detail is needed.

  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 Open Subagent MCP run. It distinguishes between 'explorer' (read-only) and 'worker' (writable) agent types, which differentiates it from sibling tools like subagent_close or subagent_rollback.

  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?

  Provides clear context: agent type selection based on need, default timeout guidelines (<=120 for normal tasks, >120 requires explicit authorizations), and note about file access. Does not explicitly list when-not-to-use, but the guidance is strong and implies appropriate use.

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

• subagent_rollbackA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries full burden. It discloses default revert of command side effects and conflict handling with force flag. However, it does not detail prerequisites (e.g., existence of recorded changes) or failure modes beyond conflicts.

  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?

  Two short paragraphs, front-loaded with the main action. Every sentence adds value with no redundancy. Efficient and to the point.

  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 an output schema (not shown) and 5 parameters, the description covers core behavior but leaves gaps: what are 'recorded file changes'? What happens if segment_id is null? No mention of error conditions or return format. Sufficient for basic understanding but not 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?

  Schema description coverage is 0%, so description must add value. It touches on parameters indirectly: rollback implies agent_id and paths; default revert relates to include_command_effects; force conflict handling. But precise semantics for segment_id and paths are absent. The description provides context but not comprehensive 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's purpose: 'Rollback recorded file changes for an Open Subagent MCP run or segment.' The verb 'rollback' and resource 'recorded file changes' are specific and distinct from sibling tools like subagent_close or subagent_spawn, which focus on lifecycle or communication.

  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 the use case (undoing changes) but does not explicitly state when not to use or compare to alternatives. Since sibling tools are clearly different (close, send_message, spawn, wait), context suffices, but explicit exclusions are missing.

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