Clipnote — turn SaaS release notes into a 60-second narrated launch video.
Scored across 2 tools
The tools have completely distinct purposes. One is for content generation (script drafting), and the other is purely for status checking of rendered video files.
The tools follow a consistent snake_case naming convention and a clear action_resource pattern (draft_script, video_status). There is no ambiguity in their naming style.
With only two tools, the set feels thin for a 'video' server. While they cover the initial stages of a workflow, the minimal count suggests it is borderline under-scoped for a comprehensive toolset.
While it covers the start (script) and a stage of the end (status), the set is notable for missing the critical step of actually creating the video from the draft script. The lifecycle is incomplete.
Draft a 40–60 second launch-video script from release notes. Free; rate-limited to 3 drafts/day per IP.
| Name | Required | Description | Default |
|---|---|---|---|
| No | |||
| product_name | Yes | ||
| release_notes | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden; it does usefully disclose cost (free) and a hard quota (3 drafts/day per IP), which is real behavioral value. However, it says nothing about whether drafts are persisted or returned inline, what the response contains, or what happens when the quota is exceeded.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, zero filler, with the core action and its constraint front-loaded ahead of the rate-limit caveat.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and no annotations means the description must cover return behavior, and it does not — an agent cannot tell if it receives a script string or a job handle (the video_status sibling hints at an async pipeline, which is never addressed). With 0% param coverage and an unexplained email field, the definition is under-specified for a 3-parameter generating tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It names release notes as the source material but says nothing about product_name's role or format, and email is entirely unexplained — an agent cannot tell whether it is required for delivery, for quota tracking, or optional contact info.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb+resource with concrete scope: 'Draft a 40–60 second launch-video script from release notes' names the output artifact, its length constraint, and the input source. It is clearly distinct from the only sibling, video_status, though it never explicitly contrasts with it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied by the artifact described; there is no statement of when to reach for this versus video_status, no prerequisites, and no note on what to do if the script needs video rendering. The free/rate-limited note is context, not routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check the render status of a Clipnote video by its access token.
| Name | Required | Description | Default |
|---|---|---|---|
| token | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. 'Check' implies a read, but it never states the operation is read-only, what status values are returned, whether it must be polled, or any rate limits. For a status endpoint with zero annotation coverage, this is thin.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single efficient sentence with the verb and lookup key front-loaded and no filler. It is appropriately sized, though it could carry a bit more without becoming bloated.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
A one-parameter lookup with no output schema needs little, and the description covers the core action. However, since there is no output schema, an agent gets no hint about what the status response contains — the one piece of context that would most help here.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and the single parameter has no description in the schema, so the description must compensate. 'By its access token' does clarify what the token identifies, adding real meaning, but it omits format or provenance details for that token.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (check) and resource (render status of a Clipnote video), and names the lookup key (access token). It is clearly distinct from the sibling draft_script, though it does not explicitly call that out.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives no when-to-use guidance, no prerequisites, and no mention of alternatives or polling behavior. An agent must infer that this is the status-polling counterpart to some render/creation tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
draft_scriptvideo_statusMake narrated, on-brand product videos of your real app from your coding agent or AI assistant.
Turn a product URL or one sentence into a launch video (MP4) with your real brand and interface.
Make how-to videos, social clips and help articles from Claude or ChatGPT, and run your help center.
Demo-video assistant: records your web app click by click and returns an MP4 with zooms, captions.
Add one secure layer between your agents and this server.