Server Quality Checklist

Tool Scores

• get_clipA
  3.7/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint true and destructiveHint false, making the read-only nature clear. The description adds detail about return field names and format (e.g., export_quality values 720p/1080p), but does not disclose other behavioral traits such as rate limits, authorization requirements, or error handling. Extra context is minor.

  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 that lists all return fields efficiently, with the purpose right at the start. No repetitive or extraneous content. Slightly dense due to the long list, but still well-structured for quick scanning.

  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 tool's low complexity (one required parameter, no output schema, no nested objects), the description covers the purpose and return fields adequately. It specifies certain field formats (export_quality values) which adds value. Some missing context about potential errors or the requirement that the clip exist, but overall sufficient.

  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 for clip_id is complete ('The unique clip ID from a project's clips array') and coverage is 100%. The description adds no further parameter semantics because the schema already provides sufficient meaning. Baseline 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 returns a JSON object with full clip details, listing specific fields. The verb 'Returns' and resource 'clip details' indicate a retrieval operation. Sibling tools like 'generate_clips' (creation) and 'list_projects' (listing) are distinct, so this tool is unambiguously for fetching a single clip's details.

  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 full details of a specific clip, but it does not explicitly state when not to use it (e.g., for listing clips) or suggest alternatives. No guidance on prerequisites (e.g., clip must exist) or context for selection among siblings.

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

• list_projectsA
  3.8/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, idempotentHint, non-destructive, openWorldHint. The description adds the response structure (fields like total, offset) but does not disclose behavioral traits beyond annotations, such as pagination defaults or rate limits.

  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: first states the return structure, second gives a usage tip. No wasted words, front-loaded with the most important information, earning its space.

  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 two parameters, full schema coverage, and no output schema, the description adequately outlines the response shape (projects array, pagination fields, project attributes). Could mention default limit (20) and max (100) from schema, but overall complete for a list tool.

  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% with clear descriptions for 'limit' and 'status'. The description adds marginal value by suggesting use of status filter for completed/failed projects, but does not provide new meaning beyond the schema's enum values.

  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 specifies it returns a JSON object with paginated list of projects and their fields (id, name, status, etc.). This distinguishes it from siblings like get_project_status (single project) or generate_clips (generation), providing a clear verb+resource scope.

  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 for listing projects with optional status filtering ('Use the status filter to find only completed or failed projects') but does not explicitly state when to prefer this tool over siblings like get_project_status or check_usage, nor are there when-not-to-use guidelines.

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

• get_project_statusA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. Description adds that download_url is only available when clip_status is 'completed' and clips sorted by score, which provides useful behavioral context beyond annotations.

  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?

  Description is detailed but each sentence contributes value: return structure, sorting, clip fields, download_url condition, polling advice. Could be slightly condensed but not wasteful.

  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?

  Despite no output schema, the description provides a comprehensive breakdown of the return object, including nested clip fields and conditional availability. Polling guidance further completes the usage context.

  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% with project_id description. Description does not add additional parameter-level meaning beyond what schema provides, but it details the return structure. Baseline 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 returns a JSON object with project status and clips, distinguishing it from siblings like get_clip (single clip) and generate_clips (creation). Specific verb 'Returns' and resource 'project status'.

  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?

  Explicit guidance: 'Poll every 10-15 seconds until project status is completed'. This is clear context for when to call repeatedly. No explicit when-not-to-use or alternatives, but the polling advice is very helpful.

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

• generate_clipsA
  4.4/5.0
  Behavior4/5

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

  The description adds context beyond annotations by detailing the return JSON structure (project_id, status, poll_url, estimated_minutes) and the async behavior with optional callback. There is no contradiction with annotations. Minor missing details like error handling or rate limits prevent a 5.

  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?

  Three concise sentences: first states purpose, second describes return, third explains async usage. Front-loaded with key information, no redundant phrases.

  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 adequately covers the return structure, async nature, and polling/callback options. Without an output schema, it provides sufficient context for an async job initiation tool. Could mention error responses or limits, but not essential.

  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 parameters are well-described in the schema. The description does not add significant new meaning beyond what the schema provides, so score remains at 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 clearly states the verb 'Start' and the resource 'AI clip generation from a YouTube video', which precisely defines the tool's action. It is easily distinguished from sibling tools like get_clip and get_project_status.

  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 explains that processing is asynchronous and provides two methods for obtaining results: polling via get_project_status every 10-15 seconds or providing a callback_url for a webhook. This gives clear when-to-use guidance.

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

• check_usageA
  4.6/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the description's addition of return format and usage context adds moderate value beyond structured data.

  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 return format and followed by usage advice, with no redundancy.

  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 zero-parameter tool, the description fully covers what the agent needs: return fields and when to call it. Output schema absence is compensated by explicit field listing.

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

  Parameters5/5

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

  With no input parameters and 100% schema coverage, the description adds no parameter info but correctly lists the return structure, fulfilling the need for parameter semantic clarity.

  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 returns a JSON object with specific fields (plan, credits_remaining, etc.), clearly distinguishing it from sibling tools like generate_clips.

  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 advises calling this tool before generate_clips to confirm sufficient credits, providing explicit guidance on when to use it and its relationship to a sibling tool.

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