Server Quality Checklist

Tool Scores

• opencode_listA
  3.9/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden. It discloses the lifetime scope and ordering, but does not explicitly state that the operation is read-only or mention any potential side effects, rate limits, or other behavioral constraints.

  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 a single, well-structured sentence that efficiently conveys all necessary information without extraneous content. It is front-loaded with the action and key details.

  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?

  Given no output schema, the description could be more complete by hinting at the structure of returned tasks (e.g., typical fields beyond status). It covers purpose and ordering adequately, but lacks details on response format for an agent to fully utilize results.

  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?

  There are zero parameters, so the baseline is 4. The description adds no parameter information (none needed), but provides context that helps understand the tool's functionality without conflicting with 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 action (list), the resource (tasks), the scope (server process lifetime), what is included (statuses), and the order (newest first). It effectively distinguishes from sibling tools like opencode_status or opencode_cancel, which operate on individual tasks.

  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 does not explicitly guide when to use this tool versus alternatives. It implies its use for an overview of all tasks, but lacks direct comparison or exclusionary language for cases when a specific task's details or cancellation is needed.

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

• opencode_statusA
  4/5.0
  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 a key behavioral trait: the status is derived from the child process's real exit event, not log string-matching, indicating reliability. This adds value beyond a simple 'get status' definition.

  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, highly concise and front-loaded with purpose. No unnecessary words, every sentence earns its place.

  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 (1 parameter, no output schema), the description adequately covers the return values and behavioral nuance. It does not address error handling for invalid task IDs, but this is acceptable for a status check 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%, so baseline is 3. The description does not add additional semantics about the task_id parameter beyond what the schema already provides ('Task id returned by opencode_dispatch').

  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 returns a structured status for a dispatched task, enumerating possible values (running, done, crashed, cancelled, unknown) and additional fields (exit code, log path). It effectively differentiates from sibling tools by focusing on status retrieval rather than dispatch, cancellation, listing, result extraction, or waiting.

  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 dispatching a task (backed by real exit event), but does not explicitly state when to use or when not to use this tool versus alternatives. No exclusions or alternative tool guidance provided.

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

• opencode_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 full burden. It discloses that the tool parses an event stream, returns structured fields (message, narration, metadata), and errors politely on unfinished tasks. This is adequate but lacks details on idempotency or side effects.

  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 sentences, front-loaded with purpose, followed by clarifying details on return fields and error condition. No fluff, every sentence adds 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?

  The description explains main return fields (message, narration) and error handling. Lacks detailed breakdown of metadata (tokens, cost, session id) and no output schema, but is sufficient for a simple 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% and the schema already describes task_id as coming from opencode_dispatch. The description adds no new parameter information beyond the schema, so baseline 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 ('Return') and clearly identifies the resource ('final assistant message and metadata'), distinguishing it from siblings like opencode_status and opencode_wait by focusing on the result content.

  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 explicitly states the tool errors if the task is still running, implying it should only be used for finished tasks. However, it does not directly compare to siblings or provide alternative usage scenarios.

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

• opencode_cancelA
  4.3/5.0
  Behavior5/5

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

  With no annotations provided, the description fully discloses the termination strategy: sends SIGTERM to the whole process group, escalates to SIGKILL after a grace period, and that finished tasks are unaffected. This is 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?

  Three sentences, no fluff. The first states the main action, the second adds escalation details, and the third covers edge cases and post-action steps. Every sentence adds value.

  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 tool has no output schema, so the description should explain the return value. It only mentions returning a note for finished tasks, but not for successful cancellations. This gap reduces completeness despite good coverage of parameters and 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?

  Schema description coverage is 100%, so the schema already documents both parameters well. The description adds context about the process group but does not significantly enhance parameter understanding 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 starts with 'Stop a running task' and details the termination process (SIGTERM then SIGKILL). It effectively distinguishes from sibling tools like opencode_dispatch or opencode_list by focusing solely on cancellation.

  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 states when to use the tool (to stop a running task) and how it handles finished tasks (returns a note). It advises polling opencode_status afterward, but lacks explicit comparison to alternatives 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.

• opencode_waitA
  4.4/5.0
  Behavior4/5

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

  No annotations provided, but the description discloses blocking behavior, a 45-second cap, and the possibility of needing to re-call. It does not cover permissions or side effects, but for a wait operation this is sufficient.

  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 with no wasted words. The purpose is stated first, followed by key behavioral details and re-call guidance.

  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?

  No output schema exists, but the description explains the return is a settled status. For a wait tool, this is adequate; sibling tools handle result retrieval. Could specify the return format more precisely, but overall complete.

  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?

  Both parameters are fully described in the schema (100% coverage). The description adds value by noting the 45-second cap and default for timeout_ms, which is not in 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 blocks on a running task until completion or timeout, specifying the verb 'block' and resource 'running task,' and distinguishes from siblings like opencode_status which presumably does not block.

  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 context for when to use: as an analog to auto-resume behavior, and advises to call again if status is still running. It does not explicitly contrast with alternative approaches like polling via opencode_status, but the guidance is clear enough.

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

• opencode_dispatchA
  4.6/5.0
  Behavior5/5

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

  With no annotations, the description carries full burden and excellently discloses key behavioral traits: directly-spawned child process, no tmux, no shared visibility into orchestration layer, and immediate return of task_id. This goes beyond a simple 'start task' statement.

  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 with zero waste. First sentence covers purpose and key behavioral traits, second sentence tells the next steps. Information is front-loaded and every word earns its place.

  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 no output schema, the description appropriately mentions returning a task_id. It covers parameter semantics well (5 params, 100% coverage) and the overall workflow is clear. Could add more about error conditions, but sufficient for correct agent usage.

  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% but description adds important context: default model value, condition that variant only applied when model is given, and that session_id resumes an existing session. This adds meaning beyond the basic 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 starts an 'opencode run' in the background and returns a task_id immediately. It uses a specific verb ('dispatch') and resource ('opencode task'), and distinguishes from siblings by mentioning subsequent polling with opencode_status and reading opencode_result.

  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 explains when to use this tool (to start a background task) and what to do next (poll with opencode_status, read opencode_result). It implies the workflow but does not explicitly state when not to use it or mention alternatives like opencode_wait for synchronous execution.

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