Server Quality Checklist

Tool Scores

• fetch_generationD
  1/5.0
  Behavior1/5

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

  Tool has no description.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness1/5

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

  Tool has no description.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness1/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Tool has no description.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters1/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Tool has no description.

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

  Purpose1/5

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

  Tool has no description.

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

  Usage Guidelines1/5

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

  Tool has no description.

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

• maintenanceB
  3.1/5.0
  Behavior1/5

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

  The annotations declare readOnlyHint=true (suggesting no side effects), but the description lists destructive operations like 'cleanup_expired: Remove expired Files API entries' and 'cleanup_local: Clean old local files', implying data deletion. This is a clear contradiction. Additionally, no disclosure of auth requirements or rate limits.

  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 uses a bullet list for operations, aiding readability. It is front-loaded with 'Perform maintenance operations'. The reference to 'workflows.md patterns' is vague but does not significantly detract. Every sentence contributes, though the external reference could be clarified.

  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?

  No output schema is present, and the description does not explain what the tool returns (e.g., a report, status, or nothing). For destructive operations, knowing the output type is important. The dry_run parameter hints at reporting, but the default behavior is unspecified. The tool's impact on data is described, but consequences (e.g., irreversible deletion) are not highlighted.

  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 parameters are already well-documented. The description adds marginal value by listing operation names with one-line summaries (e.g., 'check_quota: Check Files API storage usage'), which slightly enriches understanding beyond the schema's plain enumeration. However, for dry_run, max_age_hours, and keep_count, no additional semantics are provided.

  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 'Perform maintenance operations' and enumerates five specific operations with brief explanations (e.g., 'Remove expired Files API entries'). This distinguishes it from sibling tools (fetch_generation, generate_image, etc.) which are unrelated. The title 'Maintenance and cleanup operations' reinforces the resource.

  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 references 'following workflows.md patterns', implying a prescribed usage context, but does not explicitly state when to use this tool versus alternatives (e.g., when to choose cleanup_expired vs. cleanup_local). No when-not-to-use guidance is provided, though sibling tools are unrelated, so confusion is minimal.

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

• generate_imageA
  3.8/5.0
  Behavior2/5

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

  Annotations declare readOnlyHint=true, but description indicates mutation ('generate new images or edit existing images'), creating a contradiction. Beyond that, description discloses input file handling and return format. The contradiction significantly undermines transparency.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  Description is structured with bullet list of modes but somewhat verbose. Key information is front-loaded (first sentence captures core), but some redundancy exists (e.g., 'Supports multiple input modes:' followed by list). Adequate but not terse.

  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 complex tool with 17 parameters and no output schema, the description covers input modes, auto-detection, return type (MCP image blocks + metadata), and parameter interactions. Lacks details about metadata structure but adequate for selection and 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?

  All 17 parameters have schema descriptions, so baseline is 3. Description adds value by explaining inter-parameter relationships (e.g., file_id takes precedence over input_image_path_*) and operational context (mode auto-detection).

  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+resource: 'Generate new images or edit existing images using natural language instructions.' It lists four specific modes and distinguishes from sibling tools (fetch_generation, maintenance, show_output_stats, upload_file) by focusing on creation/editing.

  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?

  Explicitly describes when to use each mode (pure generation, multi-image conditioning, file ID editing, file path editing), including auto-detection logic. No explicit when-not or alternatives, but the context 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.

• show_output_statsA
  3.8/5.0
  Behavior3/5

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

  Annotations already provide readOnlyHint=true. Description adds context about showing stats for output directory and recent images, which aligns with read-only behavior but does not disclose potential performance impact or data freshness limits.

  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?

  Single, front-loaded sentence with no unnecessary words. Every part 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?

  Given no parameters, annotations (readOnlyHint), and no output schema, the description is mostly complete. It explains the tool's purpose but could mention what specific statistics are returned (e.g., file count, disk usage) for fuller context.

  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 exist; the input schema is empty. With 0 parameters, the baseline is 4. The description adds no parameter information, but none is needed.

  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 'Show statistics about the output directory and recently generated images', specifying the verb (show) and resource (statistics, output directory, images). It distinguishes from siblings like generate_image (creation) and fetch_generation (specific retrieval).

  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?

  No guidance on when to use this tool versus alternatives. Sibling tools are listed but the description does not explain when to prefer show_output_stats over fetch_generation or maintenance.

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

• upload_fileA
  4/5.0
  Behavior3/5

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

  Annotations show readOnlyHint=false, confirming it is a write operation. The description adds that it 'returns URI & metadata' but does not disclose potential side effects, authentication requirements, or failure behaviors. With annotations already indicating a write operation, the description provides marginal additional context.

  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 sentences, tightly worded, and front-loads the primary action and result. Every sentence serves a purpose—stating what the tool does and when to use it.

  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 low complexity (2 params, no output schema, no nested objects), the description covers the main goal and usage context. It mentions file size threshold and reusability, but lacks details on metadata format or file type constraints. Still, it is sufficient for an agent to select and invoke the tool 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 coverage is 100% with descriptions for both parameters. The description does not add significant meaning beyond the schema; it reaffirms the path is 'Server-accessible' and display_name is optional. Baseline 3 is appropriate as the schema already documents the parameters thoroughly.

  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 ('Upload a local file'), the resource ('to Polza Storage API'), and the return value ('URI & metadata'). It also provides a specific use case, distinguishing it from sibling tools that focus on generation, maintenance, or statistics.

  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 includes explicit guidance on when to use the tool: 'when the image is larger than 20MB or reused across prompts.' It does not mention alternatives or when not to use, but the context is clear given sibling tools have distinct purposes.

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