Animated word-by-word captions for your video and audio files, rendered on your machine by Cuecaps.
Scored across 2 tools
The two tools have clearly distinct roles: list_styles is for discovery of available caption styles, while studio_link is for generating a configured studio link. An agent can easily tell when to use each, and there is no meaningful overlap.
Both names use snake_case, which is readable and consistent at the casing level. However, list_styles follows a verb_noun pattern while studio_link is noun_noun, so the naming convention is not fully predictable across the set.
Two tools is very minimal and feels thin against the typical 3-15 range, even for a narrow workflow. Each tool does earn its place, but the surface is borderline under-scoped.
The server covers the full apparent workflow: discovering caption styles and generating a studio link with those settings, including instructions for export. No obvious gaps exist for the stated Cuecaps purpose.
Lists the 10 Cuecaps caption styles: the id to pass as style to studio_link, the name, and how each one looks. Call it when the user hasn't picked a style or asks what the styles look like.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description isn't burdened there. It does add behaviorally useful detail absent from structured fields: a fixed cardinality of 10 and the three attributes returned, which matters because there is no output schema. No auth, rate-limit, or pagination notes, but neither is relevant for a static enum-like list.
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 sentences, no filler. The contents of the result are front-loaded ahead of the when-to-call guidance, which is the right order for a listing tool.
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 zero-parameter, no-output-schema lookup tool; the description states the count, the fields returned, and the call condition, which is everything an agent needs. The link to studio_link closes the loop on how the output is consumed.
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?
Zero input parameters, so the baseline is 4 and there is nothing the description could add on that axis. It correctly adds the output-side meaning (id maps to the 'style' argument of studio_link), which is the only relevant parameter semantics here.
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 plus resource: 'Lists the 10 Cuecaps caption styles', and it enumerates exactly what comes back (id, name, appearance). It also explicitly ties the result to the sibling tool by naming 'style to studio_link', so an agent can separate the two without opening schemas.
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 an explicit invocation condition ('when the user hasn't picked a style or asks what the styles look like') and implicitly excludes the case where a style is already chosen. The downstream consumer (studio_link) is named, so the ordering relative to the sibling is inferable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns a link to the Cuecaps studio set up with these caption settings, and the steps to give the user: they open it, add their video, click Find words and export an MP4 with captions burned in, a transparent overlay or an SRT or VTT file. The video stays on their device. Works on every plan, Free included.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | The spoken language. Give it for any video that isn't in English; auto lets cloud transcription detect it. | |
| lines | No | Lines per caption. | |
| style | No | Caption style. list_styles shows how each one looks. | |
| words | No | Words per caption; 1 shows one word at a time. | |
| aspect | No | Frame shape: 9:16 for TikTok, Shorts and Reels, 1:1 or 4:5 for feed posts, 16:9 for YouTube. | |
| position | No | Where the captions sit in the frame. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is read-only, idempotent, non-destructive, and not open-world. The description adds meaningful behavior beyond that: it explains what the link is for, the user workflow, that video stays on the device, and that it works on every plan including Free.
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?
The purpose is front-loaded in the first sentence, and the remaining sentences add useful workflow, privacy, and plan-availability context without filler. Every part earns its place for an agent that must explain the tool to a user.
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?
There is no output schema, but the description adequately says the return includes a link and steps to give the user. It also covers privacy and plan compatibility. Minor gaps remain around link expiry or exact response shape, but the definition is otherwise complete for correct invocation.
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 description coverage is 100%, so the enum-rich parameters are already well documented in the schema. The description only refers generally to “these caption settings” and adds no parameter-specific meaning beyond what the schema provides.
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?
The description states a specific verb and resource: it returns a Cuecaps studio link configured with caption settings, plus user steps. It is clearly distinct from list_styles, though it does not explicitly name that sibling or contrast the two.
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?
The description gives clear usage context: the agent should return the link and steps so the user can open the studio, add a video, find words, and export captions. It does not state explicit when-not conditions or direct alternatives, but the intended workflow is unambiguous.
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.
list_stylesstudio_linkBurn styled, word-timed karaoke captions into any video - captions API and MCP server for agents.
One call burns captions into your video. Hosted, prepaid, no subscription. MP4 plus SRT and VTT.
Generate SRT and VTT subtitles for any video or audio file, 99 languages.
Subtitle engine for AI agents: one upload gives a written track and a translation, timings exact.
Add one secure layer between your agents and this server.
