Server Quality Checklist

Tool Scores

• run_powershellB
  3.2/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral transparency burden and does disclose meaningful traits: 'full system access', 'No restrictions', and capabilities including registry, services, network, and processes. It does not mention whether commands are destructive, what side effects might occur, or how output is returned, but the risk profile is usefully conveyed.

  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 short and front-loaded with the core action, then adds risk context and capability examples. The mention of 'No restrictions - for trusted AI partners' is slightly redundant with 'full system access', but overall there is minimal fluff and every sentence contributes useful 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?

  The description covers the safety-critical aspects of the tool and the schema documents parameters, so an agent can invoke it at a basic level. However, there is no mention of return values, error behavior, or how this tool relates to run_powershell_script, which leaves some gaps for a tool without an 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%, so the schema already documents all three parameters adequately. The description adds no additional parameter-level detail such as examples, format expectations, or timeout semantics, but since the schema covers parameters fully, the baseline 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 identifies the action ('Execute a PowerShell command') and resource, which is specific and unambiguous. However, it does not differentiate run_powershell from sibling tools like run_powershell_script, so while the core purpose is clear, the sibling boundary is not articulated.

  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 implies this tool is for arbitrary PowerShell execution with 'full system access' but provides no explicit guidance on when to choose it over run_powershell_script or avoid it in favor of safer alternatives. There are no stated conditions, exclusions, or context for selection.

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

• create_directoryB
  3.4/5.0
  Behavior3/5

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

  The description adds one meaningful behavioral detail beyond the name: 'Creates parent directories as needed.' However, with no annotations, it does not disclose failure behavior (e.g., what happens if the directory already exists) or any side effects, so it only partially carries the behavioral disclosure burden.

  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 sentences with no filler. The primary purpose is front-loaded, and the important recursive parent-directory behavior appears immediately after. 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?

  For a single-parameter tool, the description covers the core operation and a key behavior. However, it omits edge-case behavior such as error handling when the directory exists, which would be useful given there is no output schema or annotation support.

  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%, and the path parameter is adequately described as 'Directory path to create'. The description adds no additional parameter-level meaning beyond what the schema already provides, 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.

  Purpose4/5

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

  Clearly states the verb 'Create' and the resource 'directory', which is unambiguous and distinct from the sibling file/search tools. The behavior is obvious, though the description essentially restates the tool name without additional scoping.

  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?

  There is no guidance about when to use this tool versus alternatives, such as write_file or list_directory, and no mention of prerequisites or when not to use it. The usage context is only implied by the tool name and the sibling list.

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

• run_python_codeB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral disclosure burden. It usefully mentions temp file creation, execution, cleanup, and 'basic security checks,' but the security checks are vague and there is no disclosure about side effects, sandboxing, or behavior on errors.

  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 short sentences, front-loaded with the core action, followed by process and safety notes. No filler or redundant restatement of the schema.

  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?

  There is no output schema and the description does not mention what the tool returns—stdout, stderr, exit code, or result object. For an arbitrary code execution tool, missing output semantics and vague security behavior leave an agent without enough context to reliably interpret results.

  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 code, cwd, env, and timeout_ms. The description adds no additional parameter-level meaning beyond labeling the code as 'inline' and describing the temp file workflow.

  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 states a specific verb and resource: 'Execute inline Python code.' It also adds clarifying behavior (temp file, run, cleanup) that distinguishes it from file-based tools, though it does not explicitly name siblings like run_python_script.

  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 word 'inline' implies this is for code snippets rather than script files, which weakly distinguishes it from run_python_script. However, there is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named.

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

• run_powershell_scriptA
  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 the burden of safety disclosure, and it does warn about 'Full system access' and 'MCP-safe subprocess handling.' However, it does not explain that scripts can make arbitrary system changes, how errors are surfaced, or whether stdout/exit codes are returned.

  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 short sentences with the core purpose front-loaded and no filler. The risk-related warning is separated clearly and does not distract from the main action.

  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?

  All parameters are documented in the schema and the tool's risk level is stated, which covers the basic invocation requirements. However, the description omits return/error behavior and any relationship to 'run_powershell,' which leaves meaningful gaps for a high-risk execution tool with no 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%, so the schema already documents all four parameters. The description adds only 'with arguments,' which provides no meaningful semantic value beyond what the input schema already states.

  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 ('Execute') and a specific resource ('PowerShell script file (.ps1)') and explicitly mentions arguments, so an agent immediately understands the tool's function. The file-based scope also helps distinguish it from the sibling 'run_powershell' tool, which likely handles inline PowerShell commands.

  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 choose this tool over 'run_powershell' or the other script execution siblings, and it mentions no exclusions or prerequisites. 'Full system access' hints at caution, but there is no explicit decision context.

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

• run_python_scriptA
  3.6/5.0
  Behavior3/5

  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 execution happens via a subprocess and that stdout/stderr are captured, which is useful. However, it does not warn about potential side effects of running arbitrary Python code, how errors are surfaced, or whether execution is blocking—important omissions for a code execution 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 a single sentence with no filler words. It front-loads the primary action and resource, and the subprocess/output detail is brief and relevant.

  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?

  For a tool that executes arbitrary Python scripts, the description is incomplete. There is no output schema, yet the description does not explain the structure of the captured stdout/stderr result, error return behavior, or timeout implications. Critical safety context (script may have arbitrary side effects) is also missing.

  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%, and each parameter (cwd, env, args, timeout_ms, script_path) already has a clear description in the schema. The tool description adds no additional parameter meaning, so the baseline 3 applies.

  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 ('Execute') and the resource ('a Python script file'), and it differentiates from sibling tools like run_python_code by emphasizing 'script file' rather than inline code. The addition of 'with arguments' and 'captured stdout/stderr' further specifies what the tool does.

  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 for executing script files, but it does not explicitly state when to use this tool versus run_python_code, check_python_syntax, or the PowerShell siblings. No exclusions or alternative routing are provided.

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

• write_fileA
  3.6/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of disclosing side effects. It does disclose the important behavior 'Automatically creates backup of existing files', which adds value beyond just naming the operation. However, it does not mention overwrite semantics, whether directories are created, or failure behavior.

  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 short sentences that immediately state the primary purpose and then the key side effect. Every sentence earns its place, and there is no redundant or filler 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 file-writing tool with full schema coverage, the description is largely sufficient. It communicates the operation and the backup side effect, though it omits the return value and fails to specify behavior on overwrite—both useful but not blocking for a basic invocation.

  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 all three parameters, including descriptions for path, content, and create_backup. The description does not add parameter-specific meaning beyond what the schema provides, so the baseline score of 3 applies.

  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 action ('Write or update') and the resource ('a file'), so an agent can tell this is the modification tool among siblings like read_file and delete_file. It does not explicitly contrast with those siblings, but the verb is unambiguous and specific enough.

  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 intended usage is implied by the tool name and the description's verb ('write' or 'update'), but there is no explicit guidance on when to choose this over an alternative, nor any mention of prerequisites or edge cases. An agent would infer its use, but it isn't explicitly told.

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

• search_filesA
  3.7/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the burden of behavioral disclosure. It explains glob-pattern matching and wildcard support, but does not mention return format, recursion behavior, hidden files, or side-effect-free nature; 'search' does imply a read-only operation.

  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 concise sentences with no filler; the main action is front-loaded and the wildcard support example is immediately useful. Every word earns its place.

  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?

  For a simple two-parameter tool, the description plus full schema coverage is largely sufficient for invocation. However, with no output schema, the description does not state what the tool returns (e.g., list of paths) or clarify recursive search behavior, leaving minor but real gaps.

  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%, with both 'pattern' and 'directory' already described and examples given in the schema. The description's wildcard examples largely repeat those schema examples, adding minimal new meaning beyond the tool-level purpose.

  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 states a specific action ('Search for files') and mechanism ('glob patterns'), clearly identifying it as filename-pattern search. The wildcard examples further distinguish it from sibling tools like list_directory, read_file, and get_file_info.

  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 purpose implies when to use it—when you need to locate files by name pattern—but the description offers no explicit guidance about alternatives or when not to use it. No exclusions or conditions are mentioned, so the agent must infer usage context.

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

• delete_fileA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal a key behavior: a backup is created before deletion by default. However, it does not mention what happens when backup is disabled, whether deletion is permanent, or what occurs if backup creation fails.

  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 short sentences with no filler. The verb-object structure front-loads the purpose, and the backup note adds meaningful behavioral context in a compact way. 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?

  For a simple file deletion tool with fully documented parameters and no output schema, the description is nearly complete. An agent can correctly invoke it with the right parameter values and understand the default backup behavior. A minor gap is not explicitly stating the consequences of setting create_backup to false, though the schema implies it.

  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 both parameters are already documented in the input schema. The description only restates the default backup behavior and adds no additional parameter-level 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 states a specific verb and resource: 'Delete a file.' This is unmistakably distinct from sibling tools like read_file, write_file, and list_directory. The backup clause adds useful scoping without obscuring the core purpose.

  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 the tool is for deleting files, which is a clear trigger for use. However, it does not explicitly discuss when not to use it, safety checks, or alternatives. There is no direct comparison with sibling file tools, though the action itself is unique among them.

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

• get_file_infoA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It clearly indicates a read-only metadata operation and names the returned dimensions, but does not disclose error behavior, path resolution details, or what happens for missing/invalid paths.

  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, compact sentence that front-loads the action and resource while enumerating the key metadata fields. No wasted words and no repetition of the tool name.

  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 one-parameter metadata tool with no output schema, the description names the resource, the metadata included, and the path parameter. It is sufficient for an agent to invoke it correctly, though it could mention the return format or error 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 schema already fully documents the single 'path' parameter as 'File or directory path', and the description reiterates that it applies to both files and directories. Baseline 3 is appropriate because the description adds no format or additional semantic constraints 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 states a specific verb ('Get'), a clear resource ('file or directory metadata'), and specific attributes ('size, timestamps, and type'). This immediately distinguishes it from siblings like read_file (content) and list_directory (entries).

  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 the tool is for inspecting metadata rather than content or deletion, and the attribute list gives context. However, it does not explicitly say when to prefer this over read_file or list_directory, nor does it mention any exclusions.

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

• get_powershell_infoA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral disclosure burden. The verb 'Get' implies a non-mutating, read-only operation, but the description does not explicitly disclose side effects, permissions, failure modes, or output format beyond listing informational fields.

  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 efficient sentence that front-loads the primary action and resource, then lists the key informational components. Every word contributes meaning and there is no 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?

  For a zero-parameter, read-only information tool with no output schema, the description covers the essential contents of the result. It could be slightly more complete by stating the return format, but the listed fields are sufficient for an agent to correctly invoke and interpret the tool.

  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?

  The tool has zero parameters, which sets a baseline of 4. The description also adds value by indicating exactly what information will be retrieved, compensating for the lack of any schema or parameter-level 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 identifies the tool as an information retrieval operation for PowerShell and system details, enumerating specific fields such as version, OS, machine name, and user. This distinguishes it from sibling tools like run_powershell or get_python_info without ambiguity.

  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 when-to-use guidance or comparison to alternatives. The intended context must be inferred from the tool name and sibling list; for example, it does not explicitly explain that this should be used to inspect environment information before running PowerShell commands.

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

• read_fileA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful constraints ('text files', 'configurable encoding') but does not mention error handling, binary file behavior, permissions, or response format. This is adequate but not rich.

  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 concise sentence with no filler. Every word adds value, and the core action is front-loaded.

  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 tool with only two parameters and no output schema, the description sufficiently conveys that it reads file contents, supports text files, and allows encoding configuration. It does not explain return value details, but 'Read contents' makes that obvious enough.

  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 path and encoding. The description reinforces 'configurable encoding' but does not add substantial meaning beyond the schema. 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 clearly states the verb ('Read') and resource ('a file'), making the tool's purpose unambiguous. It naturally distinguishes this from siblings like write_file, delete_file, and list_directory by focusing on reading file contents.

  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 that this tool is for reading text file contents, but it does not explicitly state when to use it over alternatives like get_file_info or search_files. No explicit when-to-use or exclusions are provided, leaving the agent to infer from the name and description.

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

• check_python_syntaxA
  3.9/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the full burden of behavioral disclosure. It does disclose the most important trait—no execution—but says nothing about what happens for invalid syntax (return value, error format, exit status) or whether script_path is read safely. This leaves a meaningful 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences with no filler; the core constraint is front-loaded and the implementation detail is one short clause. Every word earns its place.

  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?

  For a two-parameter tool with full schema coverage this is close to adequate, but with no output schema or annotations, the agent is left guessing at the tool's response shape and error reporting. A brief note on what the tool returns would complete the picture.

  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%, with both 'code' and 'script_path' already described, including their mutual exclusivity. The description adds no parameter-level detail, so the baseline 3 applies.

  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?

  States a specific verb ('Check'), a specific resource ('Python code syntax'), and the key constraint 'without executing.' It also names the implementation ('ast.parse'), which makes the tool's scope unambiguous and distinguishes it from siblings that run Python code.

  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 phrase 'without executing' conveys the tool's niche: syntax validation only. However, it never explicitly names run_python_code/run_python_script as alternatives or states a when-not condition, so routing is implied rather than explicit.

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

• list_directoryA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description must carry the full behavioral burden. It discloses the output fields (names, sizes, timestamps), but does not mention hidden files, recursion depth, path-error behavior, or permissions. This is a partial but not complete behavioral disclosure.

  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, tightly worded sentence that states the action and the expected return content. Every word adds value, and there is no fluff 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?

  For a simple tool with one clearly documented parameter and no output schema, the description adequately covers what the tool does and what it returns. It is missing minor edge-case context such as recursion or error behavior, but not enough to make the description materially incomplete.

  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 fully documents the only parameter, path, with the description 'Directory path to list' (100% schema description coverage). The tool description adds no further semantic detail beyond what the schema provides, 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.

  Purpose5/5

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

  The description uses a specific verb and resource: 'List contents of a directory.' It also states the return values (file/folder names, sizes, timestamps), which clearly differentiates it from sibling tools like read_file, search_files, and get_file_info.

  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 purpose is clear enough that an agent knows to use this tool when it needs to enumerate directory contents. It does not explicitly mention alternatives or when not to use it, but the context is unambiguous, especially among the sibling file-operation tools.

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

• get_python_infoA
  4.1/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the behavioral disclosure burden. 'Get' signals a read-only introspection operation with no side effects, which is appropriate. It does not describe the exact return format or any environment-dependent quirks, but for a zero-parameter information tool the stated behavior is reasonably clear.

  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 one efficient sentence with the verb and resource front-loaded. Every phrase contributes meaning, and there is no redundant or filler content.

  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 parameterless introspection tool with no output schema, and the description provides the core expected results: version, path, and platform. An agent has enough context to decide when to call it and what it will return, without needing additional details about parameters or side effects.

  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?

  The tool has zero parameters and schema coverage is 100%, so there are no input semantics to clarify. The description adds value by naming the reported facets (version, path, platform), which helps the agent understand the response even without an output 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 uses a specific verb ('Get') and identifies a clear resource ('Python interpreter information') while enumerating concrete facets: version, path, and platform. This distinguishes it from the analogous get_powershell_info sibling and from execution-focused siblings like run_python_script.

  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 a clear use case: retrieve Python environment details before running or debugging Python code. However, it does not explicitly state when to prefer this tool over alternatives such as get_powershell_info or when it should not be used, leaving some inference to the agent.

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