Server Quality Checklist

Tool Scores

• pty_readA
  4.2/5.0
  Behavior4/5

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

  Annotations provide readOnlyHint=false, destructiveHint=true, etc., but the description adds valuable behavioral context beyond that: it explains the rolling buffer mechanism, buffer size limit (PTY_MAX_BUFFER_LINES), and that older lines are discarded, which clarifies the destructive nature. 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?

  The description is front-loaded with the core purpose, followed by structured details (modes, buffer info) in bullet-like form. Every sentence adds value—no fluff—and it's appropriately sized for the tool's complexity.

  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 and rich annotations, the description is mostly complete: it covers purpose, usage, behavior, and parameters. However, it lacks details on return format (e.g., what data structure is returned) and error handling, which could aid the agent further.

  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 all parameters well. The description adds some semantics by explaining the two modes (standard vs. search) and how offset/limit work for pagination, but this mostly reinforces rather than extends the schema details.

  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 ('Reads') and resource ('output from a PTY session's buffer'), specifying it accesses a rolling buffer. It distinguishes from siblings like pty_write (writes), pty_kill (terminates), pty_spawn (creates), and pty_list (lists sessions), making the purpose specific and differentiated.

  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 clear context on when to use it (e.g., to paginate through output, with or without regex filtering) and mentions the buffer size limit, but does not explicitly state when not to use it or name alternatives among siblings (e.g., no comparison to pty_list for session info).

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

• pty_writeA
  4.3/5.0
  Behavior4/5

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

  Annotations already indicate destructiveHint=true (mutation) and non-idempotent, but the description adds valuable context: it specifies the tool is for interactive terminal input, supports escape sequences for special keys, and provides concrete examples of common sequences. This goes beyond annotations by detailing practical behavior and input formatting.

  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 a clear opening sentence followed by bullet points and a reference table for escape sequences. It's appropriately sized for the tool's complexity, though the escape sequence table is somewhat lengthy but necessary for clarity.

  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 moderate complexity (interactive terminal input), no output schema, and rich annotations, the description is mostly complete. It covers purpose, usage, and input details but could benefit from mentioning error cases or dependencies (e.g., requires an active PTY session from pty_spawn).

  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. The description adds some value by explaining that 'data' supports escape sequences and providing examples, but it doesn't add significant meaning beyond what the schema provides (e.g., no details on 'id' format or data constraints).

  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 specific action ('Sends input data') and resource ('to an active PTY session'), distinguishing it from siblings like pty_read (receives output) or pty_spawn (creates session). It explicitly identifies the tool's function as transmitting user input to an interactive terminal.

  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 usage scenarios with bullet points: typing commands/text, sending special key sequences, and responding to prompts. It implicitly distinguishes from pty_read (for reading output) and pty_spawn (for creating sessions), though it doesn't explicitly name alternatives.

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

• pty_spawnA
  4.4/5.0
  Behavior4/5

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

  The description adds valuable context beyond annotations: it explains that sessions 'persist and allow you to' run processes, send input, read output, and manage sessions, which clarifies the tool's interactive and persistent nature. Annotations indicate it's destructive (destructiveHint: true) and not read-only (readOnlyHint: false), which aligns with 'Spawns' implying creation, but the description doesn't explicitly warn about destructive effects like resource consumption or process management risks.

  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 well-structured and front-loaded with the core purpose, followed by bullet points for key capabilities and a concluding sentence on the return value. Every sentence earns its place by providing essential information without redundancy.

  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 complexity of spawning interactive sessions and the lack of an output schema, the description is mostly complete: it explains the tool's purpose, usage, and return value. However, it could better address behavioral risks implied by annotations (e.g., destructive effects) and provide more detail on error handling or session limits.

  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?

  With 100% schema description coverage, the schema already documents all 7 parameters thoroughly. The description adds no specific parameter semantics beyond implying the command and args are for execution, and the session ID is returned for use with other tools, which is minimal added value.

  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 specific action ('Spawns a new PTY session') and resource ('pseudo-terminal session'), distinguishing it from sibling tools like pty_kill, pty_list, pty_read, and pty_write by focusing on creation rather than management or interaction with existing sessions.

  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?

  It explicitly states when to use this tool ('Unlike synchronous bash commands') and provides clear alternatives for specific use cases (e.g., 'Run long-running processes', 'Send interactive input'), though it doesn't name sibling tools directly, the context implies they are for managing spawned sessions.

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

• pty_listA
  4.6/5.0
  Behavior4/5

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

  The description adds valuable behavioral context beyond annotations: it explains that sessions remain in the list after exit until cleaned up with pty_kill, and it details the tool's role in monitoring (e.g., 'Check the status and output line count'). However, it does not fully address the annotations' hints (e.g., destructiveHint: true is not explained, and openWorldHint: true implications are unclear). No contradiction with annotations exists, but more could be said about the destructive and non-idempotent aspects.

  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 well-structured and front-loaded with a clear purpose statement, followed by a bulleted list of use cases and additional context. Every sentence earns its place by providing specific guidance or clarifying behavior, with no redundant or vague information. It is appropriately sized for the tool's complexity.

  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 (no parameters, but involves session management) and lack of output schema, the description is mostly complete: it explains what the tool does, when to use it, and key behaviors like session persistence. However, it could better address the annotations (e.g., why destructiveHint is true) and provide more detail on output format or error handling, leaving minor gaps in full contextual coverage.

  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 0 parameters and 100% schema description coverage, the baseline is high. The description adds no parameter-specific information (as there are none), but it effectively compensates by explaining the tool's output semantics (e.g., session IDs, status, output line count), which is valuable given the lack of an output schema. This enhances understanding beyond the empty input 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's purpose with specific verbs ('Lists all PTY sessions') and distinguishes it from siblings by specifying it includes 'active and exited' sessions. It explicitly mentions the resource (PTY sessions) and scope (all, including exited ones), making it highly specific and differentiated from other pty_* tools.

  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 usage guidelines with a bulleted list of when to use this tool (e.g., 'See all running and exited PTY sessions', 'Get session IDs for use with other pty_* tools'), and it implicitly distinguishes from alternatives by not overlapping with functions like pty_kill, pty_read, etc. It also clarifies that sessions remain listed until cleaned up with pty_kill, guiding when not to use this for cleanup.

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

• pty_killA
  4.9/5.0
  Behavior5/5

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

  The description adds significant behavioral context beyond annotations: it explains the status change to 'killed', the buffer retention/cleanup behavior, and the purpose of keeping sessions for log comparison. While annotations indicate destructiveHint=true, the description elaborates on what gets destroyed and under what conditions, providing valuable operational details.

  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 well-structured with clear sections (Behavior, usage advice), front-loaded with the core purpose, and every sentence adds value without redundancy. The alternative tool mention is appropriately brief and directly relevant.

  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 (destructive operation with behavioral nuances), rich annotations, and no output schema, the description provides complete context: it covers purpose, detailed behavior, parameter implications, usage guidelines, and alternatives. No significant gaps remain for agent understanding.

  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 meaningful context about parameter semantics: it explains the default behavior (cleanup=false), the implications of cleanup=true (removes session entirely and frees buffer), and ties parameter choices to usage scenarios (e.g., 'Use cleanup=false if you might want to read the output later'). This goes beyond the schema's basic 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 specific action ('Terminates a PTY session') and resource ('PTY session'), distinguishing it from siblings like pty_write (for sending signals) and pty_list/pty_read (for inspection). The title being null doesn't affect this clarity.

  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 versus alternatives: it specifies to use cleanup=false for potential future output reading and cleanup=true for complete removal, and explicitly names pty_write as an alternative for sending Ctrl+C instead of killing. This covers both when/when-not scenarios and alternatives.

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