Server Quality Checklist

Tool Scores

• how_to_connectB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden. It mentions authentication but does not explicitly disclose whether the tool is read-only, whether it triggers any side effects, or what happens when credentials are invalid. The information is not misleading but lacks explicit behavioral clarity.

  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 concise and well-structured, consisting of two sentences that clearly explain the tool's purpose and the models it supports. It avoids unnecessary verbosity while providing relevant context.

  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 description provides sufficient context for a documentation-oriented tool: it mentions the server, authentication, the range of models, client setup options, and free credits. Since there is no output schema, no return-value details are required.

  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 has no parameters (0 properties), covering 100% of the schema. The description does not add parameter-specific details because none exist. This matches the baseline for full schema coverage with no param information.

  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 clearly states the tool's purpose: to teach how to connect to the Creative Claw MCP server with authentication. It is distinct from the sibling tools (e.g., get_model_params, list_models) which focus on data retrieval rather than setup guidance.

  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 usage when needing connection instructions, mentioning setup for multiple clients and free credits. However, it does not explicitly state when to prefer this tool over alternatives or provide a clear 'use this when' condition.

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

• generate_imageB
  3.4/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden. It only mentions a connection requirement, but does not disclose side effects such as resource consumption, rate limits, or potential for cost. It also fails to mention whether the tool modifies inputs or has any destructive behavior. Minimal transparency.

  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 paragraph with two sentences, reasonably compact given the range of features listed. It is well-structured and front-loads the core purpose, but includes some redundancy (e.g., 'high-quality' and list of features). Still, it is not overly verbose.

  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?

  The description does not provide sufficient context for the agent to effectively use the tool beyond a basic prompt. It does not explain how to specify models, aspect ratios, or which editing modes are available, because those parameters are missing from the schema. The agent cannot act on the advertised capabilities, leaving critical information absent.

  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?

  The schema only includes a 'prompt' parameter with a basic description, but the tool description mentions many capabilities (model selection, aspect ratios, multi-model comparison) that would require additional parameters not present in the schema. This mismatch makes the sole parameter insufficient to execute the advertised features, confusing the agent.

  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 generates high-quality images with specific capabilities (text-to-image, image-to-image, style transfer, etc.), distinguishing it from siblings like generate_video and generate_speech. The verb 'Generate' and resource 'images' are explicit.

  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 implicitly indicates when to use this tool (for image generation) versus alternatives (video, speech) by naming the output type. It also notes a prerequisite (connection to the Creative Claw MCP server). However, it does not explicitly contrast with alternatives or state 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.

• generate_videoA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden. It mentions the requirement of a connection to the Creative Claw MCP server but does not disclose output format, asynchronous behavior, credits consumption, or other side effects. This leaves important behavioral aspects unclear.

  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 concise and well-structured, front-loading the core purpose in the first sentence. It efficiently covers supported models, generation modes, duration range, and a connection requirement without unnecessary detail.

  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 gives a good overview of capabilities and constraints but omits output details and workflow information. Given that a sibling tool check_job exists, the asynchronous nature is implied but not explained, leaving some context incomplete.

  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 describes the only parameter, prompt, as 'Description of the video to generate', giving full coverage. The tool description does not add extra parameter-level detail beyond this, so it meets the baseline but provides no additional clarification.

  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: generating cinematic video content. It distinguishes itself from sibling tools like generate_image and generate_speech by focusing specifically on video and enumerating supported generation modes.

  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 when to use the tool by mentioning video-specific capabilities, but it does not explicitly compare against alternatives or state when not to use it. There is no direct guidance for choosing between this and sibling tools such as generate_image or generate_speech.

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

• generate_speechA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description must convey behavioral aspects. It discloses a dependency on the MCP server and mentions consent-based voice cloning, implying ethical constraints. However, it does not describe potential side effects, failure modes, or whether it is a read-only or mutating operation. The creation of audio is implied but not explicitly stated.

  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 concise—three sentences efficiently cover purpose, key capabilities, and use cases. It is well-structured with a clear progression from general action to specific features and context, without superfluous details.

  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 tool with a single parameter, the description provides sufficient context: it states the action, the service used (ElevenLabs), the types of speech supported, and a prerequisite (MCP server connection). It omits explicit output details (e.g., audio file format) and alternative tool comparisons, but these are not critical for basic utilization. The description 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?

  The input schema already describes the single parameter 'text' as 'Text to convert to speech,' providing 100% coverage. The tool description adds context about multilingual and emotional speech capabilities, which enriches the meaning of text, but it does not add concrete constraints such as length limits or formatting requirements. Thus, the description adds modest value beyond the schema.

  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 with a specific verb ('Generate') and resource ('ElevenLabs models'), and lists use cases (multilingual narration, dialogue, emotional delivery) that differentiate it from sibling tools such as generate_image and generate_video.

  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 implicitly suggests usage for speech and voiceover generation by listing scenarios like video narration and audiobooks, but it does not explicitly compare with alternative tools or state when not to use this tool. The dependency on the MCP server is noted, but no explicit selection guidance is provided.

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

• get_credits_balanceA
  4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full burden. It clearly states what the tool returns (remaining balance, recent usage, and a purchase link) and notes the connection requirement. It does not specify side effects, but for a read-only balance check, this is sufficient.

  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 mostly concise but repeats the pricing model ('usage-based pricing—pay only for what you generate') which is not essential to the tool's function. It could be trimmed to focus solely on what the tool does and returns.

  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 simple no-parameter tool, the description provides sufficient context: what it does, what it returns, and a note about the required connection. No output schema is provided, but the description lists the main return elements.

  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 tool has no parameters, so the description does not need to explain any. The baseline of 4 applies as no parameter information is required.

  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: checking the current Creative Claw credits balance and usage history. It distinguishes this tool from siblings like list_models or generate_image by its specific focus on billing/credit information.

  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 indicates when to use the tool (to check balance and usage) but does not explicitly mention when not to use it or alternatives. Since there are no parameters and the purpose is self-evident, this is adequate though not explicit.

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

• list_charactersA
  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 full burden. It states the tool lists characters and mentions a prerequisite: 'Requires connection to the full Creative Claw MCP server.' It implies a read-only operation by using 'List,' but does not explicitly state side effects or error behavior, though none are expected for a listing 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 somewhat verbose and repetitive. Phrases like 'consistent multi-shot video production, UGC ads, and branded content' and 'maintain identity across generations' overlap in meaning, adding marketing fluff beyond the core purpose. A more concise wording would improve 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?

  Given no parameters and no output schema, the description is complete enough for invocation. It states the function, mentions the required server connection, and implies a list return. It lacks explicit error conditions but does not need them for basic usage.

  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 tool has zero parameters, and the schema covers 100% (vacuously). Per the rubric, a 0-parameter tool receives a baseline score of 4. No parameter descriptions are needed, and none are missing.

  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: 'List reusable Characters.' It distinguishes itself from sibling tools like list_models by specifying characters with persistent identities and optional voices, leaving no ambiguity about what is returned.

  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 explains what the tool does but does not explicitly contrast it with alternatives (e.g., when to use list_characters vs list_models). While the purpose is clear, the lack of explicit when-not-to-use guidance reduces the score from a perfect 5 to a 3.

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

• get_model_paramsA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It explicitly indicates the operation is a retrieval ('Get') and mentions a dependency ('Requires connection to the full Creative Claw MCP server'). It does not mention permissions or side effects, but for a read-only getter this is acceptable and non-contradictory.

  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 composed of four sentences, but each sentence adds value: the first defines the action and resource, the second lists the return details, the third explains the benefit, and the fourth notes a prerequisite. It is slightly longer than necessary but remains focused and free of 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?

  The description provides enough context for an agent to decide when to invoke it: it specifies the input (a specific model), the output (detailed parameters and tips), and the necessity for a connection. It lacks explicit error handling or fallback behavior, but this is not critical for a simple getter operation.

  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 covers 100% of the parameter's meaning with a detailed description that includes examples. The tool description adds no additional information about the parameter beyond reinforcing that it refers to a specific model, 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 verb 'Get' and the resource 'detailed parameters, prompting guidelines, and technical specifications for a specific AI model.' It also enumerates the returned information (dimensions, duration ranges, cost, tips), making the purpose unambiguous and distinct from the sibling list_models tool.

  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 provides clear context for when to use the tool by asserting it is 'Essential for optimizing generation quality and understanding model-specific features.' It implies that this is for retrieving details of a specific model rather than listing models, though it does not explicitly name the alternative tool.

  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?

  Given no annotations, the description carries the burden. It mentions a prerequisite (connection to MCP server) but does not explicitly state it is a read-only operation or disclose any side effects. For a simple listing, this is adequate but not fully transparent.

  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 concise and front-loaded, but includes a promotional phrase ('Access 1,000+ production-ready models') that adds little functional value. Overall it is tight and well-structured.

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

  Completeness5/5

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

  For a simple listing tool, the description is complete. It explains what will be returned, mentions the server connection requirement, and no output schema is needed. Nothing essential is missing.

  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 single parameter 'category' is well-defined in the schema with an enum and description. The main description does not add extra meaning, but the schema already provides full coverage, so the baseline is met and slightly exceeded by the concise enum explanation.

  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 identifies the tool as listing available models, with specific output details (model IDs, capabilities, cost estimates). It distinguishes itself from sibling tools like generate_image or get_model_params by focusing on the catalog discovery aspect.

  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 when the user wants to see available models before generation, but it does not explicitly mention alternatives or when not to use it. The purpose is clear enough that an agent would infer the appropriate context.

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

• check_jobA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description fully carries the burden. It discloses the read-only nature by stating 'check' and 'retrieve', lists the return fields, and notes the connection requirement. No side effects are mentioned, which is appropriate for a read operation.

  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 concise, covering all essential points in three sentences without redundant details. It is well-structured and front-loaded with the primary action.

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

  Completeness5/5

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

  Given no output schema, the description enumerates the returned data (status, progress, estimated time, URLs) and includes the prerequisite connection. This makes the tool's behavior and expectations fully clear to an agent.

  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 coverage is 100% with one parameter, and the description clarifies job_id is 'returned from a generation request', connecting it to the tool's purpose. The tool description adds context about asynchronous jobs, slightly exceeding the baseline.

  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 checks status and retrieves results of asynchronous jobs, distinguishing it from sibling generation tools. It explicitly mentions video and image generations are queued, making its purpose and scope unambiguous.

  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 after a generation call by noting video and some image generations are queued, but it does not explicitly say 'use this after generate_video' or compare with alternatives. The prerequisite about requiring the full Creative Claw MCP server is a useful usage condition.

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