Server Quality Checklist

Tool Scores

• check-predictionA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full responsibility for behavioral disclosure. It only says 'check the status' but does not clarify if the operation is read-only, whether it can be called repeatedly, or what the response format contains. Lack of side-effect information and return details leaves a transparency gap.

  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, front-loaded with the purpose, and contains no fluff. Every phrase earns its place, making it highly concise and easy to skim.

  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?

  With no output schema, the description should explain what the tool returns (e.g., status values like processing, completed, failed). It only covers the trigger condition but lacks return behavior details, making it somewhat incomplete for a simple tool that is otherwise straightforward.

  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%: the parameter 'prediction_id' is already described as returned from a previous run-model call. The description does not add extra semantics beyond the schema, so baseline of 3 applies.

  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 verb 'Check' and the resource 'the status of a running prediction', which is specific and distinct from sibling tools like run-model, search-models, and list-models. It also includes the context of a prediction_id from a prior run-model call.

  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?

  It explicitly states when to use the tool: after a run-model call returns a prediction_id with status 'processing'. This provides clear usage context, though it does not mention exclusions or alternative tools, but for this polling function the trigger condition is well-defined.

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

• run-modelA
  3.8/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It does not mention that predictions are typically asynchronous, that running a model may incur costs or take significant time, or that the response will be a prediction object rather than the final result. This is a significant gap given the dynamic nature of Replicate models.

  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, with the main purpose front-loaded and the workflow compactly stated. No wasted words; every sentence contributes actionable guidance.

  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?

  This tool has high complexity (dynamic input schema, external dependencies on get-model-info) and no output schema. The description does not explain what the tool returns or how the agent should handle the prediction lifecycle, such as polling with check-prediction. This leaves a critical gap for a multi-step workflow.

  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 detailed descriptions for both parameters, including the model identifier format and the instruction to use get-model-info for input parameters. Since schema coverage is 100%, the description adds little beyond reiterating the workflow, which is also embedded in the schema. Baseline 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 and resource: "Run a prediction on any Replicate model." This clearly states what the tool does and distinguishes it from siblings like search-models, get-model-info, and check-prediction by focusing on the action of running the prediction.

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

  Usage Guidelines5/5

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

  The description explicitly provides a workflow: if the model name is fuzzy, call search-models first, then get-model-info, then this tool. This gives clear when-to-use guidance and names the alternative tools, making it easy for an agent to sequence correctly.

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

• list-modelsA
  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 bears the full burden. It states the tool lists public models and is for browsing, which implies a read-only operation, but it does not disclose pagination behavior, authentication requirements, or response structure. This is minimally adequate but has notable gaps.

  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 with zero fluff. It front-loads the purpose and immediately provides usage guidance, making it highly efficient.

  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 with one optional parameter and no output schema. The description effectively covers purpose and usage differentiation, but it omits any mention of pagination workflow, which is partially covered by the schema's cursor description. This is a minor gap, but overall the description is adequate for the tool's simplicity.

  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 description covers 100% of the single parameter (cursor) with a clear explanation. The tool description adds no additional parameter semantics beyond what the schema already provides, 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 clearly states the tool's function with a specific verb ('List') and resource ('public models on Replicate'). It also distinguishes itself from the sibling tool search-models, making its purpose unambiguous.

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

  Usage Guidelines5/5

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

  The description provides explicit guidance on when to use this tool versus alternatives, stating 'Use search-models instead when the user mentions a specific model name' and clarifying that this tool is for browsing without a specific query.

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

• search-modelsA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description must carry the full burden. It discloses the intended agent behavior (search first, then pick best match) but does not explicitly state that the tool is read-only, describe the result format, or mention any potential side effects. The lack of a return value description is a notable gap.

  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 paragraph with an IMPORTANT warning up front. It is concise and every sentence contributes directly to the tool's usage. The heavy use of emphasis and multiple clauses makes it slightly less scannable, but it remains appropriately sized.

  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?

  Given the tool has one parameter, no annotations, and no output schema, the description is moderately complete. It explains when and how to use it but fails to describe what the results look like (e.g., fields, match quality, run count) or how many results are returned. This leaves some ambiguity for the agent when interpreting the response.

  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?

  The schema already covers the single parameter with a description and examples (100% coverage). The description adds a useful instruction: 'Use the exact text the user provided.' This supplements the schema by clarifying the expected input source and format.

  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 is for searching models, with a specific verb ('search') and resource ('models'). It also distinguishes from siblings by explicitly directing that this tool MUST be called first before any clarifying questions, positioning it as the initial lookup step.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use guidance: call this tool whenever a user mentions any model name, including fuzzy matches. It also gives exclusions: do not ask for confirmation before searching, and only ask for clarification if zero results. This effectively preempts common agent missteps.

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

• get-model-infoA
  4.6/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the full burden. It discloses that the tool returns detailed information and the input parameters schema, and that it is a prerequisite step before running a model. However, it does not describe response structure or error behavior, leaving some gaps for a no-annotation tool.

  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, front-loaded with purpose, then workflow. Every word earns its place; no redundancy or fluff.

  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 enough context for a simple lookup tool: what it does, when to call it, and how parameters relate to search results. It could mention return format more explicitly, but the phrase 'detailed information' and 'input parameters schema' gives a reasonable picture.

  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?

  The schema already covers both parameters with descriptions at 100% coverage. The description adds valuable context by explaining that these values come from search results and are used to get details for the best matching model, reinforcing the workflow and data provenance.

  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 a specific action ('Get detailed information about a specific Replicate model') and a specific resource ('including its input parameters schema'). It distinguishes itself from siblings by emphasizing per-model detail rather than listing or running models.

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

  Usage Guidelines5/5

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

  Explicit usage guidance is provided: 'Call this AFTER search-models' and 'before running it.' This positions the tool in a clear workflow relative to search-models and run-model, which are sibling tools.

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