Server Quality Checklist

Tool Scores

• list_objectsA
  4/5.0
  Behavior3/5

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

  No annotations provided, so description must disclose behavioral traits. It implies a prior connection ('connected S3 bucket') and is read-only, but does not explicitly state safety or any side effects. This is adequate but not thorough.

  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, no wasted words, front-loaded with action and result. Efficient and clear.

  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?

  No output schema, but description lists return fields. Lacks details on ordering, pagination beyond max_results, and root behavior. Sufficient for a simple list tool but could be more complete.

  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% (all parameters have descriptions). The description adds minimal extra context (e.g., 'folder path' for prefix). No significant added value 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?

  Description clearly states 'List all objects in the connected S3 bucket' and specifies return fields (name, size, date, presigned URL). It is distinct from siblings like connect_s3, read_object, and upload_object.

  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 no explicit when-to-use or alternatives are mentioned, the purpose is clear. The context of sibling tools makes usage self-evident: use this to browse objects, not to connect, read a single object, or upload.

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

• read_objectA
  4/5.0
  Behavior4/5

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

  With no annotations, the description provides good behavioral transparency: it explains format-specific behaviors (e.g., PDF first 10 pages, Parquet first 50 rows, unknown returns metadata). 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 and front-loaded with the purpose. It uses a bullet-like structure for formats, maximizing readability with minimal 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 tool without an output schema, the description adequately covers return behaviors per format. It could mention the overall return structure (e.g., JSON object) but is largely complete.

  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%, so parameters are already well-documented. The description adds no new semantic details beyond the format list, which is contextual rather than param-specific.

  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 reads and displays object contents, and lists supported formats. It is distinct from siblings like list_objects and upload_object.

  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?

  No explicit guidance on when to use this tool versus alternatives. The description focuses on format support rather than usage context or exclusion criteria.

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

• upload_objectA
  4/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It discloses the two upload modes and default behavior for object_key. However, it does not mention mandatory behavior (e.g., exactly one source required), file size limits, overwrite policy, or error handling.

  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?

  Description is extremely concise with only two short sentences plus a bullet list. Every sentence adds unique value. No fluff, front-loaded with the main verb and resource.

  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 no annotations, the description provides adequate context for a file upload tool. It explains the two input modes, optional parameters, and default key selection. Minor gaps: no mention of return value or success signal, but the essential behavior is covered.

  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%, so baseline is 3. Description adds context about default object_key and the two source scenarios, but does not go beyond the schema's parameter descriptions. No additional semantic value for parameters like bucket_name or what 'override' means.

  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?

  Description clearly states verb 'Upload a file' to a specific resource 'connected S3 bucket'. Distinguishes from sibling tools (list_objects, read_object, connect_s3) by focusing on writing. Two distinct source types (local file, internet URL) are explicitly listed.

  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?

  Description explains when to use each source (local_file_path vs source_url) and mentions optional bucket_name override. It does not explicitly state when not to use this tool or when to alternate with siblings, but the purpose is clear enough for an agent to decide.

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

• connect_s3A
  4.2/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It discloses connection modes, credential requirements, and region auto-detection, but does not mention side effects (e.g., session creation, network requirements) or whether the connection is persistent. Adequate but not comprehensive.

  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, using two sentences and bullet points. It is front-loaded with the main purpose and every sentence adds value. No wasted words.

  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 has 5 parameters, two modes, and no output schema, the description covers the accepted URL formats, mode conditions, and auto-detection. It is sufficient for an agent to understand how to invoke the tool correctly, though return value behavior is omitted.

  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%, so parameters are well-documented in the schema. The description adds extra meaning by explaining the two modes and how parameters relate (e.g., region auto-detected, credentials required for private), adding value 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 clearly states the tool connects to an AWS S3 bucket and distinguishes two modes (credentials vs public). It is specific about the resource (S3 bucket) and the verb (connect), and it differentiates from sibling tools which are object operations.

  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 explains when to use each mode: credentials for private buckets, public mode for public buckets. It provides clear context on prerequisites and auto-detection, but does not explicitly state when not to use the tool or mention alternatives beyond siblings.

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