Server Quality Checklist

Tool Scores

• tool_edit_posterB
  3.3/5.0
  Behavior2/5

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

  With no annotations, the description must disclose safety and side-effect details, but it only lists procedural steps (submit prompt, capture URL, download). It does not mention whether the operation is destructive, whether the DB is updated, or required permissions—critical gaps for a mutation tool.

  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?

  The description is a single run-on sentence that starts with the redundant 'Boss Function 3:' label. While the rest is packed with process steps, the unnecessary prefix and lack of sentence breaks reduce clarity.

  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 tool appears to be a multi-step browser automation with headless support, but the description doesn't explain prerequisites (e.g., having an existing poster in DB) or what happens if image_edit_page_url is missing. The output schema exists so return values are handled, but the workflow could use more context on state changes.

  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?

  The input schema already provides descriptions for all three parameters (headless, edit_prompt, image_edit_page_url) at 100% coverage. The description references edit_prompt and image_edit_page_url but adds no syntax or format details beyond the schema, earning the baseline 3.

  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 explicitly states the tool 'Edits/refines an existing poster image' and details the workflow, clearly distinguishing it from sibling tools like generate_poster which creates new posters. The verb 'Edits/refines' precisely identifies the operation on an existing 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 implies the tool is for refining existing posters, with 'using the image_edit_page_url stored in DB' indicating a prerequisite, but it does not explicitly state when to use this tool vs. alternatives like generate_poster or ratio_editor. It provides context but no explicit exclusions or alternative suggestions.

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

• tool_create_projectA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description carries the transparency burden. It discloses the mutation side effect of saving to db/projects.json and notes aspect ratio selection, but it omits details about idempotency, error/failure behavior, or how headless mode affects execution.

  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 a single, front-loaded sentence that efficiently covers the main actions and side effects. The 'Boss Function 1:' prefix is unnecessary but does not significantly harm clarity.

  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?

  The tool is simple (2 parameters, no nested objects) and includes an output schema, so the description does not need to explain return values. It adequately covers creation, DB persistence, and ratio selection, but lacks usage guidance and headless behavior details.

  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 schema already fully documents both parameters. The description adds minimal extra meaning by referencing 'selects the desired aspect ratio,' but it does not clarify the headless parameter beyond its schema default.

  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+resource ('Creates a new Google Flow project page') and adds a unique side effect ('saves the project URL to DB'), clearly distinguishing this creation tool from sibling poster-related tools. It also mentions the aspect ratio selection, aligning with the input schema.

  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 explicit when-to-use guidance, exclusions, or alternatives are provided. The description only states what the tool does, leaving the agent to infer that it should be used for creating a project rather than editing or generating posters.

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

• tool_generate_posterA
  3.7/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of disclosure. It transparently describes side effects ('records the image_edit_page_url in DB', 'downloads 1K output') and specific UI interactions ('pastes input images and prompt onto the canvas', 'clicks Send'), going well beyond a simple 'generates a poster' phrase.

  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 a single sentence but is slightly cluttered by the 'Boss Function 2:' prefix, which is superfluous. The core information is front-loaded and each step contributes to understanding the tool's behavior, though the dense chain of actions could be broken down for readability.

  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?

  An output schema exists, so return value details are not required. The description covers the full workflow, side effects, and key parameters (via schema). It doesn't mention prerequisites like needing an existing project or setting up Google Flow, but given the optional parameters and self-contained description, it is reasonably 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 description coverage is 100%, so the schema already documents each parameter (prompt, headless, image_paths, project_url). The description only loosely references 'input images and prompt', which adds no additional meaning beyond the schema. Baseline 3 applies because the schema does the heavy lifting.

  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 'Generates a poster in Google Flow' and enumerates a concrete sequence of actions (paste images and prompt, click Send, open edit page, record URL, download output). This specific workflow distinguishes it from sibling tools like tool_edit_poster and tool_poster_ratio_editor, which focus on different poster-related operations.

  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?

  The description provides no explicit guidance on when to use this tool versus the sibling tools. It does not mention alternatives, exclusions, or conditions under which another tool would be more appropriate. The workflow implies poster generation, but no comparative context is given.

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

• tool_poster_ratio_editorA
  3.9/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the multi-step process, including reliance on db/projects.json, the prompt submission, URL capture, and image download. However, it does not disclose potential side effects (e.g., whether it modifies the DB) or any environmental requirements, leaving minor gaps.

  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 a single, dense sentence that efficiently captures the entire process. The 'Boss Function 4:' prefix is unnecessary noise, but the rest of the sentence is information-dense without redundancy. It is reasonably concise and well-structured.

  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 100% schema coverage, presence of an output schema, and a thorough step-by-step description, the tool is well-contextualized. The only missing element is explicit when-to-use guidance, but overall the description is sufficient for an agent to understand the tool's operation and 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?

  The schema already provides 100% coverage with detailed descriptions for all four parameters, so the baseline is 3. The description references the ratio and prompt in the workflow, but adds no additional semantic detail beyond what the schema already states. No compensation 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 the specific workflow: opening the latest edit page from DB, selecting the target aspect ratio, submitting the prompt, capturing the updated URL, and downloading the image. This distinguishes it from sibling tools like tool_edit_poster, which likely handle general edits, by focusing solely on ratio editing.

  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 the tool is used for changing image aspect ratio and downloading the result, but it does not explicitly state when to use this tool versus alternatives, nor does it mention any exclusions or when-not-to-use conditions. It lacks direct comparison with sibling tools.

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