Server Quality Checklist

Tool Scores

• merge_imagesA
  3.9/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral disclosure burden and does disclose two key traits: it consumes credits from the configured account and returns a task id for polling (async behavior). It does not mention failure modes or rate limits, but the most consequential side effects are surfaced.

  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 front-loaded, with the core action in the first sentence and behavioral details in the second. The website URL is slightly extraneous for an AI agent but does not undermine the overall conciseness.

  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 no output schema, the description appropriately mentions the return value (task id for polling) and cost implication. Given the sibling get_merge_status exists, an agent can infer the next step, though a brief mention of checking status via that tool would make it fully 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 baseline applies; all four parameters are already documented in the schema. The description adds only the 'public' and 'exactly two' constraints, which are also present in the schema, so it provides no significant meaning beyond it.

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

  Purpose4/5

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

  The description states a specific action ('Combine exactly two public JPG, PNG, or WebP image URLs') and a clear result ('into one AI-generated image'). It does not explicitly name the sibling get_merge_status, but the note about returning a task id for polling signals the async workflow and helps differentiate it from status polling.

  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?

  Clear context is provided: the tool is for merging two public image URLs, with prerequisites explicitly mentioned (public, supported formats, exactly two). It omits explicit when-not-to-use guidance, but with only one sibling (a status poller), the usage context is sufficient.

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

• get_merge_statusA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It effectively communicates that this is a status-checking/read operation that returns the image URL only once the asynchronous merge is ready. It could add detail on in-progress or failed states, but the core async behavior is disclosed.

  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 first sentence is compact, front-loaded, and informative. The second sentence adds a website URL that is not directly useful for invoking the tool correctly, so the description is not perfectly economical, but it remains short and clear.

  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?

  There is no output schema and no annotations, so the description needs to cover the return behavior. It explains that the image URL is returned when ready, but it does not describe what the tool returns for pending or failed tasks, which is important for an agent trying to poll or handle errors.

  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%, and the schema already explains that taskId is the id returned by merge_images. The description does not add meaningful new semantics beyond that, so the baseline score of 3 is appropriate.

  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 ('Check'), names the resource ('status of an image merge task'), and ties the task to merge_images. It clearly distinguishes this polling tool from the creation-oriented sibling merge_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 phrase 'created by merge_images' makes clear that merge_images must be called first, and 'when it is ready' implies polling behavior. However, it does not explicitly say 'use this tool after merge_images to poll until ready' or mention when not to use it.

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