Server Quality Checklist

Tool Scores

• read_zip_contextA
  3.8/5.0
  Behavior4/5

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

  With annotations already indicating read-only and idempotent behavior, the description adds valuable context: operates entirely in memory, does not extract to disk, applies filtering categories, and returns a virtual file tree and text contents. No contradictions with 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 a single, information-dense sentence that front-loads the main verb and object, then packs in filters, return type, and safety behavior without redundancy or waste.

  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 core purpose, return type, and safety aspects, and annotations cover the read-only profile. However, it omits explanations for the optional parameters and does not address edge cases (e.g., password-protected zips, empty archives). Given low schema coverage, these are notable gaps.

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

  Parameters2/5

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

  Schema description coverage is only 33% (only 'path' has a description). The description does not compensate for undocumented 'max_files' and 'max_output_bytes'—it doesn't mention them or explain their function. The filtering categories listed are internal behaviors, not parameter meanings, leaving the agent without guidance.

  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 purpose: 'Inspect a .zip archive entirely in memory' with specific filtering and return behavior. It distinguishes itself from sibling tools (read_code_context, analyze_images) by focusing on ZIP archives and in-memory processing.

  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 context implies this tool is for reading ZIP archives, but the description does not explicitly mention when to use it versus alternatives or state exclusions. It lacks guidance like 'for code files use read_code_context' or 'not for large archives beyond limits'.

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

• read_code_contextA
  4/5.0
  Behavior4/5

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

  Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds valuable behavioral detail beyond annotations: it does not follow symlinks and filters out vendor/build folders, binaries, and secret files. This explains the 'clean' output promise. It could further clarify edge cases (e.g., behavior with missing paths or the effect of max_files), but the added filtering context is meaningful.

  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, well-structured sentence that front-loads the core action ('Read a source file or directory'), then incrementally adds the filtering rules and the return behavior. Every clause adds information and there is no redundancy or filler.

  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 core purpose and the most important filtering behaviors, and annotations cover safety. However, it omits details about the two limit parameters, the exact structure of the returned tree/contents, and any error behavior. Given the absence of an output schema, these gaps leave the description not fully self-sufficient for an agent making invocation decisions.

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

  Parameters2/5

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

  Schema description coverage is only 33% (only 'path' has a description). The description does not compensate for the under-documented 'max_files' and 'max_output_bytes' parameters; it only reiterates that 'path' can be a file or directory, which the schema already says. The two limiting parameters remain unexplained, and the description adds no new semantic value for them.

  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 ('Read') plus a clear resource ('a source file or directory') and elaborates with filtering criteria (no symlinks, omits vendor/build folders, binaries, secrets) and a stated output ('clean tree and contents'). This clearly differentiates it from sibling tools like analyze_images and read_zip_context, which target different content types.

  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 implies usage for reading source code while excluding non-essential or sensitive files, giving clear context. However, it does not explicitly state when to prefer this tool over the listed siblings or provide exclusion criteria (e.g., 'for images use analyze_images'). It lacks explicit alternatives or when-not-to-use guidance.

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

• analyze_imagesA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable context such as resizing, strict processing order, and the use of specific external models (Gemini, OpenAI, OCR), which justifies the expected behavior. It doesn't mention potential network dependencies or rate limits, but the core behavioral traits are disclosed.

  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, dense sentence that front-loads the action and follows a logical sequence (resolve, resize, analyze, return). Every clause contributes information, with no filler 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?

  With only 2 parameters and no output schema, the description provides a fairly complete picture of the workflow and the return format ('delimited JSON context'). It could be more specific about the JSON structure and any prerequisites, but given the annotations and simplicity, it's adequate.

  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 descriptions already cover both parameters at 100% coverage. The description enriches the meaning by specifying that image_paths are local/OpenCode references, that order matters for analysis, and that images are resized—details not present in the schema. It also ties the prompt to the analysis focus implied by the pipeline.

  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 specific verbs ('Resolve', 'resize', 'analyze') and names the resources (local/OpenCode image paths) and the processing pipeline (Gemini, OpenAI, OCR). It clearly distinguishes from sibling tools like read_code_context and read_zip_context, which target code and zip files, not images.

  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 clearly states the tool is for analyzing images and outlines the ordered process, making it obvious when to use it. It doesn't explicitly exclude other tools, but the sibling names (read_code_context, read_zip_context) show they serve different content types, so the context is clear.

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