Server Quality Checklist

Tool Scores

• pictory_transcribeC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description must carry the full behavioral disclosure burden. It does not mention that transcription is job-based via job_id, that webhook_url is supported, or that highlight extraction requires an explicit action. The phrase 'automatically extract' is slightly misleading because the schema requires a separate action.

  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 one front-loaded sentence with no filler, listing the two main outcomes in order of importance. It is concise, though it sacrifices operational detail.

  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 is an 8-parameter multi-action tool with no annotations, yet the description provides only a one-line overview. An agent would not know that certain actions require job_id, that transcript_text applies only to generate_highlights_from_transcript, or that clip generation has its own workflow; the output schema does not compensate for that missing invocation 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 description coverage is 100%, so the baseline applies; the schema already documents job_id, video_url, max_duration, and the other parameters. The description adds only loose context ('long-form', 'viral short clips') and no action-specific parameter guidance.

  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 clear action, 'Transcribe long-form videos/podcasts', and a secondary outcome, 'extract viral short clips'. It does not explicitly contrast siblings like pictory_video or enumerate the action parameter's modes, so it ffall short of 5.

  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?

  There is no guidance on when to use this tool instead of siblings, and no advice about which action value matches which workflow. The only implicit signal is the transcription/clip phrasing, which is insufficient for a multi-action tool.

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

• pictory_videoC
  2.9/5.0
  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 of behavioral disclosure. It discloses the general capability set but not important behavioral traits: operations appear to be asynchronous or job-based (poll_job), some actions require prior job IDs, and update_elements patches a storyboard rather than performing a full render. These are meaningful behaviors that an agent would need to understand before invoking the tool.

  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 concise sentence with no filler, front-loading the resource and core operations. It is appropriately terse, though for a six-operation dispatcher tool it could afford slightly more structure without becoming 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?

  For a multi-action tool with six parameters and an output schema, the description is too thin. It does not explain the relationship between actions, the expected workflow sequence (render_storyboard, create_preview, render_from_preview, render_project), or the polling requirement. The presence of an output schema reduces the need to explain return values, but the missing operational context is a significant gap.

  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 is 3. The description itself adds no parameter-level meaning beyond the schema, which already documents each parameter including the action enum values and the conditional need for job_id in certain operations.

  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 resource ('Pictory videos') and a clear set of operations ('Create, render, preview, and patch'), which distinguishes it from sibling tools focused on transcribe, assets, projects, and integrations. It is clear at a high level, though it does not explicitly differentiate itself from those siblings or explain what 'patch' means operationally.

  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 gives no guidance on when to use this tool versus pictory_projects, pictory_transcribe, or pictory_assets. It does not mention workflow ordering, prerequisites, or exclusion conditions. The action parameter lists possible operations, but the description itself does not help an agent choose this tool over alternatives.

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

• pictory_integrationsB
  3.1/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses state-changing behavior through action verbs like 'Cancel', 'Delete', 'Disconnect', 'Authorize', 'Connect', and 'Remove', and labels clean_job as affecting 'stuck/failed' jobs. However, it does not disclose consequences, reversibility, permissions, or side effects beyond the surface action, so transparency is partial.

  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 starts with a one-sentence overview and then uses a clean bullet list where each action has an inline command snippet and a short gloss. It is long, but the length is warranted by the 14 actions. No wordy filler is present, though a legend for parameter usage would be more efficient than repeated endpoint notation.

  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?

  For a complex multi-action dispatcher with 6 parameters and no annotation coverage, the description is incomplete. It fails to specify which parameters are required for each action, what connection_payload should contain, the valid values for action, or how list actions use pagination. The output schema's existence doesn't compensate for missing operation-to-parameter mapping, so an agent cannot reliably construct valid requests.

  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?

  Schema description coverage is 0%, so the description must compensate. It lists action names and endpoints including {id} placeholders, implying job_id and connection_id usage, but it never explicitly maps schema fields (action, page, page_size, connection_payload, job_id, connection_id) to actions. The connection_payload parameter is not mentioned at all, and page/page_size are undocumented.

  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 domain ('Manage third-party cloud integrations, account quotas, AI credits, and job cleanup') and enumerates 14 specific actions with endpoints and one-line behaviors. It distinguishes itself from siblings like pictory_video and pictory_transcribe through its focus on integrations, quotas, credits, and jobs. The verb 'Manage' is broad, but the action list provides concrete specificity.

  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?

  Usage is implied through each action's description (e.g., 'Cancel or delete a stuck/failed job' tells when clean_job is appropriate), but there is no explicit guidance on when to use this tool vs. sibling tools like pictory_video or pictory_projects. No exclusions or alternatives are named, leaving tool selection to inference from the action list.

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

• pictory_assetsB
  3.4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full behavioral burden. It usefully separates read-style actions (search/list) from generative actions, discloses HTTP methods and endpoints, and lists model names. However, it does not mention auth requirements, possible costs or latency of AI generation, or side effects such as asynchronous asset creation.

  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 overview sentence front-loads scope, and each supported-action bullet is compact and adds an endpoint plus action-specific detail. The list is long, but the tool genuinely dispatches 13 actions, so the length is mostly justified; only minor redundancy with the opening summary exists.

  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 enumerates all action surfaces and key model values, which is strong for a dispatcher tool. However, action-specific input requirements are missing, such as needing a prompt for AI generation or file metadata for upload URL generation. An output schema exists, so return values are covered, but input construction is still partly underspecified.

  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 0% across 18 parameters, so the description must compensate. It does add real value by enumerating valid action values, AI model choices, and some filter values like moods/genres/instruments. But it never maps several parameters (service, category, style, aspect_ratio, reference_image_url, file_name/file_type) to their specific actions or value formats.

  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 overview sentence names concrete resources (stock b-roll, music, voices, avatars, layouts, AI Studio media) and specific actions (search, list, generate), and the action list adds endpoint-level detail. It is clear enough to separate asset discovery from transcription or project tools, though it never explicitly contrasts itself with sibling tools like pictory_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 implies the tool is for asset search and AI-generated media, but it provides no explicit when-to-use versus when-not-to-use guidance relative to siblings. The overlap between generate_ai_video here and a tool like pictory_video is not resolved, leaving the agent to infer routing.

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

• pictory_projectsB
  3.4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It discloses useful behavioral traits such as 'auto-concurrency retry' and 'schema protection' for update_scene and indicates mutation via PUT/DELETE methods. But it does not explain side effects, reversibility, permission requirements, or synchronization/caching behavior in enough depth.

  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 opening sentence gives an immediate summary, and the bulleted action list is compact with endpoints. Some statements are repetitive with the schema (e.g. list actions only restate endpoint names), and the tail becomes slightly garbled, but overall the structure is scannable and front-loaded.

  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?

  For a multi-action dispatcher with 15 parameters, no annotations, and no schema field descriptions, the definition is incomplete. It never specifies which parameters apply to which actions, how payload should be structured for update actions, or the meaning of library, page/page_size, asset_id, file_path, and media_url. The output schema reduces the return-value burden, but invocation details remain under-specified.

  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?

  Schema description coverage is 0%, so the description must compensate for 15 parameters. It explicitly names only a few param-related concepts (project_id, template_id, text, duration, scenes, footage, thumbnail) and leaves payload, library, asset_id, file_path, media_url, page, page_size, and description undefined. It is insufficient for correctly constructing most invocation payloads.

  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 that this tool manages Pictory projects and master video templates, and then lists every supported action with HTTP methods and endpoints. The resource scope (projects/templates) is distinct from the sibling tools (video, integrations, transcription, assets), so an agent can identify what it does without opening the schema.

  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 provides clear action-level semantics (list, get, update, delete, create) and notes full web UI synchronization, which implies when the tool is relevant. However, it never explicitly tells the agent when to prefer this tool over a sibling or when not to use it, nor does it state prerequisites or exclusions beyond the action list.

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