Server Quality Checklist

Tool Scores

• list_directoryA
  3.6/5.0
  Behavior3/5

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

  Annotations already provide readOnlyHint and idempotentHint, so the safety profile is covered. The description adds the permission-boundary behavior ('許可フォルダ内') beyond annotations, but does not disclose other behaviors like non-recursive listing or behavior when the path is invalid.

  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, front-loads the action and scope, and contains no redundant words. Every part contributes to the meaning.

  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 one-parameter, read-only tool with an output schema, the description covers the essential behavior and the authorization scope. It is slightly incomplete only in not specifying whether the listing is immediate children or recursive, which would make it fully unambiguous.

  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 path parameter is already documented. The tool description adds no parameter-specific detail beyond the schema, only the general allowed-folder constraint; baseline 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 uses a specific verb ('返します') and resource (files/folders in a folder), and adds the scope constraint '許可フォルダ内' (within an allowed folder). It clearly describes the tool's function, though it does not explicitly call out how it differs from list_allowed_directories or read_file.

  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 this tool is for listing the contents of a folder under an allowed root, but it does not state when to prefer this over list_allowed_directories or read_file, nor does it mention prerequisites such as first discovering the allowed folders. Usage context 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_allowed_directoriesA
  4/5.0
  Behavior3/5

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

  Annotations already provide readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds the useful scope that only server-authorized directories are returned, but it does not disclose other behavioral details such as ordering, errors, or permission-related failure modes. There is no contradiction with the 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 one compact Japanese sentence with no filler. It front-loads the resource and action clearly, making it easy for an agent to parse quickly.

  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 parameterless, read-only, idempotent tool with an output schema, the description is nearly complete. The only minor gap is that it does not explicitly connect the returned directory list to the sibling file-operation tools, but this is not necessary for correct invocation.

  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, so there are no parameter semantics to document. The description appropriately focuses on what the tool returns. Baseline 4 is appropriate for a parameterless tool.

  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 names a specific verb and resource: it returns the list of folders the server is permitted to read and write. This clearly distinguishes it from siblings like list_directory, read_file, and write_file, which operate on directory contents or files rather than on the authorization boundary.

  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 use—discovering which directories are accessible before using file tools—is implied by the description, but it does not explicitly state when to use this tool instead of alternatives or mention any exclusions. No direct routing guidance to sibling tools is provided.

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

• write_fileA
  4/5.0
  Behavior4/5

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

  The annotations already signal destructiveness (destructiveHint=true). The description adds valuable behavioral detail by explicitly stating that existing files are overwritten and that append=true appends instead. This goes beyond the annotation without contradicting it.

  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?

  A single, focused sentence that front-loads the core action and constraint, with a parenthetical clarifying the append option. No wasted words or redundancy with the schema.

  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 annotations covering safety, the schema covering parameters, and an output schema present, the description covers the essential behavior (overwrite vs. append) and scope. Nothing critical is missing for a competent agent to invoke it correctly.

  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 parameters are already fully documented. The description adds minimal extra meaning beyond the schema, mainly reinforcing the overwrite/append behavior already visible in the schema defaults and 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 action ('書き込みます' — writes) and the resource ('ファイル' — file), and explicitly notes the allowed-folder scope. This sets it apart from sibling read/list tools without any ambiguity.

  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 usage context is implied: it handles writes within the allowed folder, while siblings handle reading and listing. However, it does not explicitly mention when to prefer this tool over read_file, or what conditions would make writing inappropriate.

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

• read_fileA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and idempotentHint=true, so the safe, non-mutating behavior is covered. The description adds useful scope constraints beyond the schema: text files only, and only within permitted folders. There is no contradiction with the 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?

  A single, front-loaded sentence conveys the operation, resource type, and scope restriction with no redundant words. It is appropriately sized for a simple read tool.

  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?

  For a low-complexity read tool, the description, annotations, full schema coverage, and presence of an output schema collectively leave no critical gap. The important contextual restriction—allowed-folder scope—is explicitly stated.

  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 'path' and 'encoding' are already documented in the input schema. The description does not add parameter-specific meaning, but at full schema coverage 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 names a specific verb (reads and returns) and a precise resource (contents of text files in allowed folders). This clearly distinguishes read_file from siblings like list_directory, list_allowed_directories, and write_file.

  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 gives clear context: use this tool when you need the content of a text file within the allowed folder. It does not explicitly mention alternatives or when-not-to-use conditions, but the purpose is unambiguous enough to infer the correct choice from sibling names.

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