Server Quality Checklist

Tool Scores

• get_caller_identityA
  4.3/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=true, indicating a safe read operation. The description adds value by specifying the return format (dictionary with success and identity fields). No contradictions.

  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, with three sentences. The first sentence states the main purpose, and the following sentences add return details. No unnecessary 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?

  Given zero parameters, the presence of an output schema, and annotations providing readOnlyHint, the description is complete. It explains what the tool returns without needing to cover output schema details.

  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?

  No parameters are defined, so schema coverage is 100%. The description does not need to add parameter semantics; baseline 4 is appropriate for zero parameters.

  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 it 'Get the AWS identity of the current caller' and mentions specific returned fields (Account, ARN, UserId). This is a specific verb+resource combination that distinguishes it from siblings like call_aws and suggest_aws_commands.

  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 (retrieve caller identity), but there is no explicit guidance on when not to use it or how it compares to siblings. The description lacks alternative recommendations or exclusions.

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

• call_awsA
  4.4/5.0
  Behavior4/5

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

  Annotations already indicate destructiveHint=true, so destructive potential is known. The description adds behavioral context: default region (us-east-1), working directory, and file path requirements. It also states validation and error handling are present. The description does not contradict annotations (no annotation_contradiction). Some additional detail about what could be destroyed (e.g., data operations) would be beneficial, but overall it's adequate.

  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-organized with sections for key points, command restrictions, examples, and return info. Every sentence adds meaningful guidance without redundancy. It is front-loaded with the core purpose and usage instructions. At approximately 150 words, 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 (executing arbitrary AWS CLI commands), the description covers essential operational constraints (syntax, restrictions, working directory, default region) and provides multiple examples. The presence of an output schema (not shown but confirmed in context) reduces the need to detail return values, though the description gives a high-level summary. The description is sufficiently complete for an agent to use the tool 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?

  Schema description coverage is 100% (both cli_command and max_results have descriptions). The description adds value beyond schema by emphasizing that cli_command must start with 'aws', providing usage examples, and clarifying that max_results is for pagination. The schema alone would not convey these usage 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 tool executes AWS CLI commands with validation and error handling. It distinguishes itself from siblings like 'suggest_aws_commands' which suggests commands, and 'get_aws_regions' or 'get_caller_identity' which retrieve specific data. The verb 'Execute' plus resource 'AWS CLI commands' is specific and unambiguous.

  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 explicitly says to use this tool when you know the specific AWS service and operation, and provides a list of restrictions (no pipes, redirects, shell variables) and required syntax (command must start with 'aws'). Examples illustrate proper usage. It does not explicitly contrast with sibling tools for when not to use, but the guidance is clear enough for an agent.

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

• get_aws_regionsA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true (safe) and openWorldHint=false (fixed result set). The description adds the return structure (dictionary with success status and list), providing useful behavioral context beyond annotations. No contradictions.

  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 extremely concise with two sentences, no filler, and front-loaded purpose. Every word earns its place, making it efficient for an agent to parse quickly.

  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 has no parameters, annotations cover safety, and an output schema exists (implied return structure), the description is complete. It states exactly what the tool returns, leaving no gaps for an agent to misinterpret.

  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 no parameters, so the description naturally adds nothing about them. Schema coverage is 100% (0 params). Baseline for 0 params is 4, and the description meets that without needing to compensate.

  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 'Get a list of available AWS regions'. It distinguishes from siblings like 'call_aws' (which makes API calls), 'suggest_aws_commands' (which suggests commands), and 'get_caller_identity' (which gets identity), making the purpose specific and unambiguous.

  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?

  While the description does not explicitly provide when-to-use or alternatives, the purpose is self-explanatory for a simple list retrieval tool. The context of siblings implies its role. A more explicit guideline would elevate this, but for a trivial tool, it is sufficient.

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

• suggest_aws_commandsA
  4.7/5.0
  Behavior5/5

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

  Annotations declare readOnlyHint=true, and the description confirms a read-only operation by describing the return as a dictionary of suggested commands. It adds transparency about the output structure, which annotations do not cover.

  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 yet comprehensive: purpose, usage guidance, examples, and return description. Every sentence adds value, and the structure is front-loaded with the core function.

  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 simplicity (single parameter, no nested objects, output schema mentioned), the description fully covers the purpose, usage, and behavior. Annotations and context signals do not leave gaps.

  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 input schema defines a single 'query' string parameter with examples. The description enriches this by advising on query formulation (include service name, action, context), which adds semantic guidance beyond the schema. Schema coverage is 100%, so the description lifts the baseline.

  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 function: 'Suggest AWS CLI commands based on a natural language query.' It specifies the verb (suggest) and resource (AWS CLI commands), distinguishing it from sibling tools like call_aws (execution) and get_aws_regions (retrieval).

  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 explicitly advises when to use this tool: when unsure about command syntax or exploring commands. It provides best practices for query formulation and includes examples. While it doesn't directly contrast with siblings, the implicit guidance is clear.

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