Server Quality Checklist

Tool Scores

• list_top_processesC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description alone is responsible for disclosing behavioral traits. It only states 'List top N memory-consuming processes' but fails to mention important behaviors like default values (n=10, max=100), the ability to sort by CPU, or any specifics about output. This is a significant transparency gap.

  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, front-loaded sentence with no wasted words. It efficiently communicates the core purpose, though it lacks structure for detailing options or usage. This is appropriately concise for a simple tool.

  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 is relatively simple, and an output schema exists, so return value details are unnecessary. However, the description is minimal and does not address the ambiguity with sibling tools like 'list_memory_usage' or mention sorting flexibility. It is adequate for a basic understanding but lacks completeness for effective tool selection.

  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 for both parameters (n and sort_by) with clear descriptions, so the baseline is 3. The tool description does not add parameter semantics, but the schema handles it. However, the description mentions only 'memory-consuming' while sort_by can be 'cpu', which is slightly misleading, though the schema clarifies this.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states a specific verb ('List') and resource ('top N memory-consuming processes'), making the tool's primary function unambiguous. However, it does not explicitly differentiate from sibling tools like 'list_memory_usage', which could overlap in purpose, so it falls short of a 5.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives such as 'list_memory_usage' or 'find_stale_processes'. It gives no context, exclusions, or preferred use cases, leaving the agent without enough information to select between siblings.

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

• find_stale_processesB
  3.3/5.0
  Behavior2/5

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

  With no annotations provided, the description must disclose behavioral traits. It implies a read-only search operation ('Find...') and mentions 'potentially stale' but does not explicitly state that it performs no destructive actions, whether results are limited, or any side effects. The heuristic nature of 'potentially' is vague and lacks detail about how staleness is determined beyond what the schema already shows.

  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 concise and front-loaded: the first sentence states the primary action, and the second adds a clear use case. Every word contributes value with no repetition or filler.

  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 4 optional parameters and an output schema, so the schema fills in some gaps. However, the description does not clarify what constitutes 'stale' (e.g., age, memory, state) beyond the parameter names, and it fails to mention relationships to sibling tools. For a moderately complex tool, this leaves some gaps in understanding when and how to invoke it effectively.

  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 100% coverage for all 4 parameters, each with clear names, defaults, and descriptions. The tool description adds no parameter-specific information beyond what the schema already documents, so the baseline score of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool 'finds potentially stale processes' with a specific verb and resource. It distinguishes itself from siblings (like list_top_processes or kill_processes) by focusing on staleness rather than general listing or termination. However, it doesn't explicitly name alternative tools or contrast its behavior.

  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 provides helpful context ('Useful for finding long-running background processes that may be consuming resources unnecessarily'), implying when to use it. It does not mention when to avoid it or offer alternatives like list_top_processes, so the guidance is present but incomplete.

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

• list_process_groupsA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the burden. It states that it returns grouped stats and gives an example, but it does not specify which stats are included (e.g., CPU vs memory) or potential edge cases, leaving some gaps.

  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 concise sentences, front-loaded with the primary action and followed by a helpful example. No unnecessary words or repetition.

  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?

  With an output schema present and schema descriptions covering parameters, the description is largely complete. It provides a clear purpose and an example. It could mention read-only behavior, but that is implied by 'List' and the output schema.

  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% for both parameters (n and min_count), with clear descriptions and defaults. The tool description adds no additional meaning beyond the schema, so 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 clearly states the tool lists processes grouped by name with aggregated stats, using a specific verb and resource. This distinguishes it from sibling tools like list_top_processes (individual processes) and list_memory_usage (memory-specific).

  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 a clear use case: 'Useful for seeing total resource usage by process type' with an illustrative example. However, it does not explicitly mention alternatives or exclusions, so it falls short of a 5.

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

• kill_processesA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of disclosing behavior. It covers critical safety traits: refuses PID 0/1, root-owned checks, optional name confirmation, and signal defaults. It stops short of explaining what happens when a refusal occurs or how partial failures are handled, but the core behavioral profile is well covered.

  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 succinct and well-structured, with a clear opening statement followed by a bulleted list of safety mechanisms. Every sentence is informative, with no filler or 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?

  The tool has moderate complexity (3 params, output schema present). The description covers the essential behavior and safety constraints. It doesn't discuss outcome reporting or edge cases like already-terminated processes, but the existence of an output schema reduces the need to describe return values. Overall, adequately complete for its complexity.

  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 baseline is 3. The description adds value beyond the schema by clarifying that SIGKILL is only used when explicitly requested and that name confirmation aborts kills on mismatch, which are constraints not fully spelled out in the parameter 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 'Kill processes by PID', which is a specific verb+resource pair. It is distinctly different from sibling tools that list or find processes, leaving no ambiguity about its function.

  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 for when to use this tool (to terminate processes) and highlights safety mechanisms, making the intended use obvious. It doesn't explicitly exclude scenarios, but none of the sibling tools perform killing, so the usage is unambiguous.

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

• list_memory_usageA
  4.5/5.0
  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 indicates a read-only operation through 'Get' and 'Returns', and the `free -h` analogy strongly implies a non-destructive system query. It does not explicitly state that it makes no system changes or require permissions, but for a simple query tool this is effectively conveyed.

  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 exactly two sentences, front-loaded with the main purpose, and then adds specific return fields and a useful analogy. Every sentence contributes value with no redundancy.

  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?

  This is a simple tool with no parameters and an output schema. The description fully explains what it does and what metrics it covers, and the `free -h` analogy provides familiar context. There are no missing pieces for an agent to invoke it correctly.

  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, and the schema confirms this. The description adds no parameter details because none exist. Per the rubric, a baseline of 4 is appropriate for 0-parameter tools.

  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 'Get' and the resource 'system memory usage summary', and further specifies the fields returned (total, available, used memory, swap statistics). This distinguishes it from sibling process-focused tools, and the analogy to `free -h` reinforces its purpose.

  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: use it to obtain a memory usage summary. It doesn't explicitly mention alternatives or exclusions, but the sibling tools are all process-related (e.g., list_top_processes, kill_processes), so the intended use case is obvious. No explicit 'when-not' is stated, but the scope is unambiguous.

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