This server enables AI clients to control Divoom smart watches/displays over LAN, exposing watchface management, device control, and design assistance tools.
Watchface Management
Retrieve current or specific local watchface info
Patch existing watchfaces (font, color, layout, dial background) via JSON diffs or multipart uploads
Replace only the dial background image without changing other config
Create brand-new local watchfaces from images or asset bundles
Reset local watchfaces back to their cloud version
Browse store/market watchface listings
Display & Device Control
Switch the active watchface by ClockId
Adjust screen brightness (read/write)
Turn the screen on or off
Capture a screen snapshot (.webp) for visual verification
File & Asset Management
Upload arbitrary files to the device via multipart POST
Font & Element Discovery
List fonts available on the device
Query a catalog of 194 firmware-supported display element types (filterable by id, name, type)
Query a curated font catalog with style tags, script support, and scenario recommendations
Layout & Template Assistance
Search ~20 curated watchface skeleton templates to clone layouts
Get layout hints (position, size, color, alignment) for specific display element types
Protocol & Debugging
Retrieve protocol quick-reference guides and safety rules
Send arbitrary raw commands to the device's /divoom_api endpoint for advanced operations
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-divoom-lan show me the current watchface on my Divoom device"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-divoom-lan is an open-source MCP server that wraps Divoom watchface LAN APIs as standard tools for AI clients.
It works together with the v2 HTML visual editor for modifying watchfaces, switching faces, adjusting brightness, and creating new local watchfaces.
v2 visual editor (public):
GitHub: https://github.com/DivoomDevelop/divoom-watchface-visual-editor_v2
Live site: https://divoomdevelop.github.io/divoom-watchface-visual-editor_v2/
Your local clone path (e.g. D:\divoom-watchface-visual-editor) is machine-specific; use the v2 GitHub / GitHub Pages URLs above in docs and MCP metadata.
Expose key capabilities from Divoom_Watchface_Remote_Customization_Guide_EN.md as MCP tools
Let MCP-enabled clients (Cursor, Claude Desktop, local LLMs, etc.) drive watchface actions via natural language
Preserve safety boundaries (read before write, explicit warnings for risky operations, multipart rules)
Related MCP server: @qirabot/mcp
Read before write: call watchface_get_local, then watchface_patch_local, then read back to verify.
If GetLocalClockInfo returns an empty ItemList: stop writes; switch to an editable watchface first.
Do not call watchface_create_local_clock unless the user clearly asks to create a new one (no implicit creation).
watchface_get_local → Device/GetLocalClockInfo
watchface_patch_local → Device/PatchLocalClockInfo (default /divoom_api); optional dialAssetsPath switches to multipart POST /patch_local_clock (same dial/tar.gz rules as watchface_create_local_clock)
watchface_get_fonts_local → Device/GetLocalFontList
watchface_get_store_market_list → Device/GetStoreClockMarketList
watchface_set_clock_select → Channel/SetClockSelectId
watchface_get_brightness → Sys/GetBrightness
watchface_set_brightness → Channel/SetBrightness
watchface_onoff_screen → Channel/OnOffScreen (1=on, 0=off)
watchface_replace_dial_bg_file → POST /replace_clock_dial_bg
watchface_upload_file → POST /upload
watchface_create_local_clock → POST /create_local_clock (multipart: single dial image or tar.gz; JSON DialAssets/UseDialAssetBundle selects mode, default auto-detect gzip)
watchface_reset_local_then_cloud → Device/ResetLocalClockFromServer
watchface_get_screen_snapshot → Device/GetScreenSnapshot (wait 2s, then GET /userdata/snapshot.webp for visual diff)
watchface_raw_command → generic POST /divoom_api
watchface_protocol_quick_reference → key protocol constraints for the model
The server exposes two MCP resources:
divoom://guide/quick-reference
divoom://skill/watchface-customization
For MCPB-compatible hosts (e.g. Claude desktop connectors, Smithery stdio releases), build a local bundle:
Install the packer: npm install -g @anthropic-ai/mcpb
From this package root: npm run mcpb:pack
Output: mcp-divoom-lan.mcpb (gitignored). The staging directory mcpb/staging/ is also gitignored.
The bundle includes dist/, resources/, production node_modules, and a manifest.json with user fields for device IP, port, and timeout.
cd tools/mcp-divoom-lan # or your clone root for this package
npm install
npm run build
npm startDevelopment (watch rebuild):
npm run devPre-release check (typecheck, build, pack dry-run):
npm run release:checkdocs/README.md — documentation index
docs/quick-start.md — minimal setup
docs/tool-examples.md — tool usage examples (includes §5b analog pointer layout)
docs/disp-usage.md — choosing disp ids (pointer layout 131/132/233; net-gallery uniqueness 13/125–130/173–175)
docs/html-visual-editor.md — using the visual editor with MCP
docs/safety-and-troubleshooting.md — safety and FAQs
docs/reference/ — condensed protocol rules (EN/ZH)
docs/examples/ — sample requests/responses and catalog
DIVOOM_DEVICE_HOST — device LAN IP (e.g. 192.168.1.120)
DIVOOM_DEVICE_PORT — HTTP port, default 9000
DIVOOM_TIMEOUT_MS — request timeout ms, default 45000
If DIVOOM_DEVICE_HOST is unset, each tool call must pass target.host.
{
"mcpServers": {
"divoom-lan": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/to/tools/mcp-divoom-lan/dist/index.js"
],
"env": {
"DIVOOM_DEVICE_HOST": "192.168.1.120",
"DIVOOM_DEVICE_PORT": "9000",
"DIVOOM_TIMEOUT_MS": "45000"
}
}
}
}You can also copy client-config.example.json in this directory as a starting point.
Use a dedicated repo (e.g. mcp-divoom-lan) with this package at the repo root.
Verify metadata: LICENSE, SECURITY.md, CONTRIBUTING.md, CHANGELOG.md, RELEASE.md as applicable.
Run npm run release:check.
Tag a GitHub release (e.g. v0.1.2) with screenshots and sample requests if helpful.
Submit listings where appropriate (MCP Registry, Smithery, Glama, MCP.so, community indexes). For Glama, follow GLAMA_SUBMISSION_READY.md (includes Dockerfile and glama.json). For MCP.so, follow MCP_SO_SUBMISSION_READY.md. For 火山引擎 MCP 清单，见 VOLCENGINE_SUBMISSION_READY.md（PR: https://github.com/volcengine/mcp-server/pull/398）。For 阿里云百炼自定义 MCP（控制台 npx 部署），见 BAILIAN_MCP_SUBMISSION_READY.md。For 扣子 Coze 插件发布/商店（HTTP 插件，与 MCP 不同），见 COZE_SUBMISSION_READY.md。
Minimal demo flow: watchface_get_local → watchface_patch_local (font size/color) → watchface_replace_dial_bg_file (background).
Included in this repo (when present): LICENSE, CHANGELOG.md, CONTRIBUTING.md, SECURITY.md, RELEASE.md, optional checklist and directory templates, and .github/workflows/ci.yml.
Recommendation: no for the core MCP package — keep MCP lean. Offer the editor as a separate optional project.
Core: https://github.com/DivoomDevelop/mcp-divoom-lan
Visual editor v2: https://github.com/DivoomDevelop/divoom-watchface-visual-editor_v2
Hosted v2: https://divoomdevelop.github.io/divoom-watchface-visual-editor_v2/
Benefits:
Small MCP install suitable for all AI clients
Non-developers can use the visual UI to understand ItemList, then let the AI apply patches
Clear split between WYSIWYG editing and automated MCP writes
This repo ships standalone docs under docs/, docs/reference/, and docs/examples/. If you maintain full guides elsewhere, keep this tree synced or treat it as the distribution subset.
POST /create_local_clock (multipart) — Device/CreateLocalClock. metadata.DialAssets accepts 'auto' (default; sniffs gzip magic on the file part), 'image' (single JPEG/WebP backdrop), or 'bundle' (clock_bg.tar.gz). Legacy UseDialAssetBundle (0=image, non-0=bundle) is honored when DialAssets is omitted. Backdrop is JPEG/WebP only; element slots inside the tarball accept JPEG/WebP/PNG (firmware wf_validate_bundle_slot_image_file). Each ItemList[i] needs disp/font/x/y/w/h/size/alig numbers and color_1/color_2/item_id non-empty strings; ItemIdList must be a parallel non-empty string array. alig: 3=center, 4=left, 5=right. Pointer slots DIVOOM_CLOCK_DISP_SUPPORT_HOUR_POINT_IMAGE=131, MIN_POINT_IMAGE=132, SECOND_POINT_IMAGE=233: mandatory shared square w=h and identical x,y,w,h on all three rows; w×w bitmaps; center pivot, hand toward 12 o'clock — never full-screen 800×1280 layers or mismatched thin rects; reference ClockId 60012 export. transp: MUST use 100 for visible layers — LLMs often emit 0 → invisible on device. hier: ONLY 0=auto, 1=bottom, 2=top (no tier 3+). See docs/tool-examples.md §5b. Uniqueness: do not duplicate the same image-backed disp in one dial — later rows overwrite earlier ones; especially NET_PIC family (disp 13, 125–130, 173–175, DIVOOM_CLOCK_DISP_SUPPORT_NET*_PIC); see docs/disp-usage.md. Multipart framing (Content-Length per part): see watchface_upload_file description.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. | |
| imagePath | Yes | Either a single JPEG/WebP dial backdrop (recommend 800x1280, ≤ 500 KiB) or a `clock_bg.tar.gz` USTAR+gzip archive. Tar contents: required `clock_bg.jpg|webp` at the root plus one file per local leaf referenced by `ItemList[i].image_addr` (no subdirs, leaf basenames ≤ 95 bytes). Leaves may be JPEG/WebP/PNG; non-supported sources should be transcoded client-side. | |
| metadata | Yes | First multipart JSON: `ClockName`, `ItemList`, `ItemIdList`. Optional `DialAssets` (`auto`|`image`|`bundle`) or legacy `UseDialAssetBundle` (0/!=0). In bundle mode, `ItemList[i].bundle_image` is an alias for `image_addr` leaf and is also accepted. Tool minifies the JSON before sending. | |
| filePartName | No | Second multipart part name. Default is current UTC ms timestamp. | |
| fileName | No | Filename in multipart header. Defaults to basename(imagePath). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden and is exceptionally transparent. It details DialAssets modes, legacy handling, slot constraints, pointer requirements, transparency settings, hierarchy rules, and uniqueness warnings. All critical behaviors are disclosed.
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 description is very long and dense, containing extensive technical details. While structured in a logical flow, it could be more concise to improve readability without losing critical information.
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?
Given the tool's complexity (5 parameters, nested objects, no output schema), the description is remarkably complete. It covers almost every aspect of usage, from multipart framing to specific slot requirements and common pitfalls.
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 100%, but the description adds significant value by explaining valid values, legacy behavior, and constraints beyond the schema. For example, it clarifies DialAssets options, image format restrictions, and pointer slot rules.
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 clearly states the tool's action (create local clock via POST multipart) and the resource. However, it does not explicitly distinguish from sibling tools like watchface_patch_local or watchface_replace_dial_bg_file, missing some differentiation.
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?
No explicit guidance on when to use this tool versus alternatives. The description is purely technical and does not provide context on scenarios or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the full disp id catalog (194 entries) that the firmware understands for ItemList[i].disp and ItemPatchList[i].patch.disp. Each entry includes English symbol, Chinese description, and heuristic hints (likelyUsesRasterOrAssetLayer for image/GIF slots; oftenUsesVectorFontForText for text slots). Use it together with watchface_font_catalog: text-leaning disps need a font id; raster-leaning disps need an image_addr asset.
| Name | Required | Description | Default |
|---|---|---|---|
| ids | No | Return only the entries whose disp id is in this list. | |
| nameContains | No | Case-insensitive substring filter on the English symbol (e.g., 'WEATHER'). | |
| descriptionContains | No | Case-insensitive substring filter on the Chinese description (e.g., '日历'). | |
| expects | No | 'image' = only slots whose hints.likelyUsesRasterOrAssetLayer is true; 'text' = only slots whose hints.oftenUsesVectorFontForText is true. | |
| limit | No | Max entries to return (default 80, max 300). | |
| idsOnly | No | If true, return only `[{disp, name, description_zh}]` rows for a compact summary. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Discloses return fields (symbol, description, hints), filter parameters, defaults (limit default 80), and no side effects. Could mention if read-only implicitly, but behavior is clear for a catalog retrieval.
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, first sentence upfront states purpose and key details, second sentence provides usage context. No redundant information; every word contributes value.
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?
Description is fairly complete for a catalog retrieval tool: states entry count, fields, and usage with sibling tool. No output schema, but description implies structure. Slight gap in not explicitly stating return format (array of objects) but overall adequate.
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%, each parameter already has a description. The description adds little beyond schema: it references hints (image/text) which maps to the 'expects' enum, but does not add new semantic meaning. Baseline 3 is appropriate.
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 clearly states the tool returns the full disp id catalog (194 entries) firmware understands, specifies entry contents (English symbol, Chinese description, heuristic hints), and explicitly distinguishes its use from sibling tool watchface_font_catalog by explaining the relationship between disp and font/image requirements.
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?
Explicit guidance: 'Use it together with watchface_font_catalog' and explains when each type applies ('text-leaning disps need a font id; raster-leaning disps need an image_addr asset'). This provides clear context for when to use this tool vs alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return a curated font catalog so agents can pick ItemList[i].font ids deterministically. Each entry includes id, type (1=TTF, 0=image-font), display name, original charset, derived script (digits / digits-extended / latin / cjk), style tags (sans/serif/pixel/digital/handwriting/display/decorative/bold/light/etc), and recommendedFor (scenario names like time_digits / temperature_digits / weather_text / user_text / lunar_text). The response also includes a scenarios map that lists which disp ids each scenario covers and which tags to prefer. For visual style and mood per font id, read MCP resource divoom://font/guide first. Use the optional filters to narrow the result. Always cross-check with watchface_get_fonts_local before committing a font id to a real device, because the on-device font list may be a subset.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Filter by font type. Default 'all'. | |
| script | No | Filter by derived script. 'digits' = image fonts whose charset is exactly 0-9. | |
| tag | No | Match a single style tag (e.g., 'pixel', 'digital', 'handwriting', 'sans', 'serif', 'cjk-capable'). | |
| scenario | No | Filter to fonts whose `recommendedFor` includes this scenario (see top-level `scenarios` map for the full list). | |
| ids | No | Return only the entries whose id is in this list (useful after watchface_get_fonts_local). | |
| limit | No | Max number of font entries to return (default 50, max 200). | |
| idsOnly | No | If true, return only `[{id, name, type_name, script}]` rows for a compact summary. | |
| includeScenarios | No | If true (default), include the top-level `scenarios` map in the response so the agent can map disp ids → preferred tags. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, but the description explains the response structure (entries with fields, scenarios map) and filter effects. It does not mention authentication or error handling, but for a read-only catalog query, it is sufficiently transparent about what the tool returns and how it behaves.
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 description is well-structured and front-loaded: first sentence states purpose, then details output, then usage guidance. Every sentence adds necessary value without redundancy. It efficiently conveys all essential information.
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?
Given 8 optional parameters and no output schema, the description is quite complete. It explains the output fields, scenarios map, recommends cross-checking and visual resource. Missing details like default filter values (except limit) and error handling, but overall sufficient for an agent to use the tool appropriately.
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 100%, so baseline is 3. The description adds value by explaining how parameters like 'ids' are used after watchface_get_fonts_local, and the 'includeScenarios' parameter affects response structure. It also ties filters to narrowing results.
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 clearly states it returns a curated font catalog for deterministic font ID selection, details the output fields (id, type, name, etc.), and distinguishes from sibling 'watchface_get_fonts_local' by explicitly advising cross-check with that tool.
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?
It provides explicit when-to-use guidance (pick font IDs), recommends using optional filters, and advises always cross-checking with watchface_get_fonts_local before committing. It also suggests reading MCP resource for visual style.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Call Sys/GetBrightness.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must disclose behavior. 'Call Sys/GetBrightness' reveals no behavioral traits such as side effects, permissions, or rate limits. It does not even confirm it is 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise but at the cost of substance. Front-loading is irrelevant because there is only one short phrase; it is under-specified rather than efficiently spare.
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?
For a tool with one nested parameter and no output schema, the description should explain the action and return value. 'Call Sys/GetBrightness' is insufficient.
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 100% with descriptions for all parameters, so the baseline is 3. The description adds no value beyond the schema; it does not mention parameters at all.
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 'Call Sys/GetBrightness' barely clarifies the purpose beyond the tool name. It indicates calling a system function for brightness but lacks specificity on what it retrieves or the context. It does not differentiate from 17 sibling tools.
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?
No usage guidelines are provided. The description gives no advice on when to use this tool versus alternatives, no prerequisites, and no context for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Call Device/GetLocalFontList.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behaviors. It only states the call action, with no mention of side effects, permissions, rate limits, or whether it is read-only. The tool likely retrieves data without modification, but this is 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
While very short, the description is too vague to be considered concise in a helpful way. It sacrifices informativeness for brevity and does not earn its place with actionable content.
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?
Given no output schema, the description should explain return values or response format. It does not. The tool likely returns a list of fonts, but this is absent, leaving agents underinformed.
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 100%, so the schema already describes the target parameter and sub-properties. The description adds no new semantic value 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?
Description states the tool calls Device/GetLocalFontList, which clarifies it retrieves local fonts. However, it does not distinguish from sibling tools like watchface_font_catalog, leaving ambiguity about when to use this one.
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?
No guidance on when to use this tool versus alternatives, nor any context about prerequisites or constraints. The description is purely operational.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Call Device/GetLocalClockInfo for current or explicit clock id.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. | |
| clockId | No | ||
| useCurrentDisplayClock | No | ||
| parentClockId | No | ||
| parentItemId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully convey behavioral traits. It only mentions a remote API call but gives no details about side effects, authorization requirements, or failure modes. Transparency is minimal.
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 description is a single sentence, which is concise. However, it could be structured better with line breaks or bullet points for readability. Nonetheless, it is not verbose.
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?
Given the tool has 5 parameters, a nested object, and no output schema or annotations, the description is severely incomplete. It fails to provide enough context for an agent to use the tool correctly.
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 only 20%, yet the description adds virtually no meaning beyond the schema. It vaguely references 'current or explicit clock id' but does not explain the target object, parentClockId, or parentItemId parameters.
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 the tool calls Device/GetLocalClockInfo for a clock id, but it does not clarify what information is returned or how it differs from sibling tools like watchface_get_fonts_local or watchface_get_brightness. The purpose is vaguely defined.
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?
No usage guidelines are provided. The description does not indicate when to use this tool versus alternatives, nor does it mention any prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Call Device/GetStoreClockMarketList after device prefetch has populated in-memory store data.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It only states the API call and prerequisite, omitting details on idempotency, auth, rate limits, or safety. No behavioral traits are disclosed.
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?
Single sentence is concise and front-loaded with the action. Could include more useful info without being wordy, but maintains efficiency.
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?
Given no output schema and no annotations, the description should explain return values and error conditions. It only mentions calling an API, leaving the agent without sufficient context.
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% for the single optional 'target' parameter. The description adds no parameter information, so baseline 3 applies.
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?
Description states it calls a specific API endpoint but does not explain what the endpoint does, making the purpose vague. It is not a tautology but lacks clarity on what 'store market list' means.
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?
Only mentions a prerequisite ('after device prefetch has populated in-memory store data') but provides no guidance on when to use this tool versus alternatives or 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.
Return layout hints for a single disp id by combining disp-catalog metadata with aggregated typography (median size/x/y/w/h, frequent colors, alignment mode) mined from bundled marketplace templates. Use before authoring a new ItemList row or ItemPatchList.patch fragment — values are soft guidance, not firmware-enforced. Always clamp boxes to the logical canvas (typically 800×1280).
| Name | Required | Description | Default |
|---|---|---|---|
| disp | Yes | Target ItemList[i].disp. | |
| canvasWidth | No | Logical canvas width for clamp reminders (default 800). | |
| canvasHeight | No | Logical canvas height for clamp reminders (default 1280). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses key behaviors: results are aggregated from templates, soft guidance, and a requirement to clamp boxes to the canvas. It does not cover side effects or permissions, but is sufficient for a read-only tool.
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 description is three sentences, front-loading the core purpose. Every sentence is essential, with no repetition or filler.
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?
The tool has no output schema, so the description should clarify return value structure. It only says 'Return layout hints' without specifying format. Given moderate complexity and no annotations, this is a notable gap.
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?
The input schema already describes parameters with 100% coverage. The description adds value by explaining the role of disp (target list item) and the logical canvas sizes for clamping, enhancing understanding beyond the schema.
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 clearly states the tool returns layout hints for a single disp id, combining metadata and aggregated typography. It distinguishes itself from sibling tools by specifying its unique function.
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 advises using this tool 'before authoring a new ItemList row or ItemPatchList.patch fragment', providing clear context. It also notes that values are soft guidance, not enforced, which helps set expectations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Call Channel/OnOffScreen with OnOff (1=on, 0=off).
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. | |
| onOff | Yes | 1 turns screen on, 0 turns screen off. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It mentions it calls a channel endpoint, implying a network operation, but omits side effects, error modes, or whether the action is reversible. The description is minimal.
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 description is a single sentence, extremely concise. However, it sacrifices explanatory content for brevity. It is front-loaded with the core action.
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?
Given no output schema and a nested target object, the description fails to explain the remote procedure, what the return value might be, or how to set up the connection. It is incomplete for a tool that likely sends an HTTP command.
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 100%, so the baseline is 3. The description adds that onOff is '1=on, 0=off', which repeats the schema. The 'target' parameter is not elaborated beyond the schema. No significant extra meaning.
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 clearly states the tool calls 'Channel/OnOffScreen' with an on/off parameter and maps 1=on, 0=off. This distinguishes it from sibling tools which manage other watchface aspects like brightness, fonts, or clocks.
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?
No guidance is provided on when to use this tool versus alternatives, nor does it mention prerequisites like device connectivity or typical scenarios. The description is purely operational.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Patch local dial via Device/PatchLocalClockInfo with precheck. Defaults to POST /divoom_api (JSON only) for pure metadata edits. Prefer ItemPatchList (per-index field diff) — DO NOT include item_id inside patch.* unless the user explicitly asks to rename a slot, since the firmware will overwrite the device-side item_id and break menu/config bindings. When dialAssetsPath is set, switches to multipart POST /patch_local_clock: first JSON part (Device/PatchLocalClockInfo, optional DialAssets), second part single JPEG/WebP dial backdrop or clock_bg.tar.gz bundle. Element slots inside the tarball must be JPEG, WebP, or PNG (validated by firmware wf_validate_bundle_slot_image_file). Use ItemPatchList[].patch.bundle_image= to bind a tar leaf to that slot's img_addr; supplying ItemList alone is a full-table replace and should be avoided unless the row count actually changes. Pointer fixes (131/132/233 = DIVOOM_CLOCK_DISP_SUPPORT_*_POINT_IMAGE): shared square x/y/w/h, w×w PNGs, center rotation; ref ClockId 60012; transp 100; hier 0/1/2 only — docs/tool-examples.md §5b. Avoid duplicate image-backed disp rows (NET_PIC family); docs/disp-usage.md. Multipart framing: watchface_upload_file description and resources/skill-quick-reference.md.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. | |
| clockId | No | ||
| useCurrentDisplayClock | No | ||
| deviceImageUrl | No | ||
| devicePreviewImageUrl | No | ||
| devicePreviewImageUrl2 | No | ||
| setColorList | No | ||
| itemList | No | ||
| itemIdList | No | ||
| itemPatchList | No | ||
| itemPatchByRoleList | No | ||
| dialAssetsPath | No | Optional second multipart part. Either a single JPEG/WebP dial backdrop (`clock_bg.jpg|webp`, validated by divoom_watchface_replace_clock_dial_bg_validate_saved_file) or a `clock_bg.tar.gz` bundle. The tarball may contain `clock_bg.jpg|webp` plus the leaves listed by `ItemPatchList[].patch.bundle_image`. Element leaves inside the tar may be JPEG/WebP/PNG (PNG is element-only; backdrop must be JPEG/WebP). When set, the tool POSTs `/patch_local_clock` with the firmware-strict multipart layout. | |
| filePartName | No | Multipart field name for dialAssetsPath part. Default is current UTC ms timestamp. | |
| fileName | No | Multipart filename header for dialAssetsPath. Defaults to basename(dialAssetsPath). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given no annotations, the description covers many behavioral aspects: default POST method, switching to multipart when dialAssetsPath is set, validation by firmware, warnings about item_id breaking bindings, and pointer fix details. It lacks rate limits or side effects but is generally transparent.
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 description is a dense wall of text with no paragraph breaks or structure. It is not front-loaded and contains tangential details. Could be significantly streamlined and organized.
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?
Despite the tool's complexity (14 parameters, nested objects, no output schema), the description omits return values and does not cover several parameters. It provides deep detail on specific aspects but is incomplete overall.
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 only 29%. The description elaborates on dialAssetsPath and some aspects of itemPatchList, but many parameters (e.g., clockId, useCurrentDisplayClock, deviceImageUrl, setColorList, itemIdList) are not explained. The description fails to compensate for low schema coverage.
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 clearly states the tool patches local dial via Device/PatchLocalClockInfo with precheck, and distinguishes two modes (JSON-only for metadata, multipart for assets). However, it does not explicitly differentiate from sibling tools like watchface_create_local_clock or watchface_replace_dial_bg_file, leaving some ambiguity.
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?
Internal usage guidance is provided (prefer ItemPatchList, avoid item_id in patches), but there is no high-level statement on when to use this tool versus siblings, nor conditions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return concise operational constraints extracted from the public guide and skill.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It fails to state whether the tool is read-only, what data it accesses, or any side effects. The phrase 'return concise operational constraints' suggests a read operation, but no further details.
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?
Single sentence, front-loaded, no extra words. However, conciseness sacrifices clarity; a slightly longer description would improve utility.
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?
The tool has no output schema and no annotations. The description provides insufficient context for an agent to understand what 'operational constraints' means or how to interpret the return value. A reference tool needs explicit output specification.
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?
There are zero parameters, so schema coverage is 100% and the description adds no value for parameters. Baseline 3 applies, but the description should still clarify the overall function, which it does not do well.
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?
Description is vague: 'concise operational constraints' does not specify what kind of constraints or how they are returned. It lacks a concrete verb and resource, and does not differentiate from sibling tools like watchface_get_local or watchface_font_catalog.
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?
No guidance on when to use this tool versus the many siblings. It does not mention prerequisites, context, or alternatives, leaving the agent to guess.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Raw POST /divoom_api command wrapper. Command is required; payload object is merged with enforced ReturnCode=0.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. | |
| command | Yes | ||
| payload | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavioral traits. It mentions 'enforced ReturnCode=0' but fails to cover error handling, side effects, authentication, rate limits, or idempotency. The lack of warnings about using a raw command is a significant gap.
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 sentence that is front-loaded with the tool's purpose ('Raw POST /divoom_api command wrapper') and then immediately explains the key details. Every word earns its place; no redundancy.
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?
Given the tool's raw nature and 17 siblings, the description lacks essential context: return values, error handling, command examples, and payload constraints. Users are left guessing, increasing risk of misuse.
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 low (33%), so the description should compensate. It clarifies that 'command' is required and 'payload' is merged with ReturnCode=0. However, it doesn't explain valid command values or payload structure, leaving much ambiguity.
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 clearly states it's a raw POST /divoom_api command wrapper, identifying the verb and resource. It distinguishes from sibling tools that are higher-level operations (e.g., watchface_set_brightness). However, 'raw' is vague and doesn't fully detail when to prefer this over alternatives.
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?
No explicit guidance on when to use this tool vs the many sibling tools. The description implies usage for arbitrary commands, but there's no mention of when not to use it or what alternatives exist. A dedicated 'when to use' section is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
POST /replace_clock_dial_bg using multipart (Device/ReplaceClockDialBgFile). Replaces the cached dial bitmap only — does NOT modify cfg DeviceImageUrl, and does NOT accept tar.gz. Backdrop is validated by divoom_watchface_replace_clock_dial_bg_validate_saved_file: JPEG (FF D8) or WebP (RIFF…WEBP) only, ≤ 500 KiB (DIVOOM_REPLACE_DIAL_BG_MAX_FILE_BYTES), recommended 800x1280 portrait. Multipart framing notes: watchface_upload_file description.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. | |
| imagePath | Yes | Absolute or relative image file path. Backdrop must be JPEG (FF D8) or WebP (RIFF…WEBP); PNG/GIF are rejected. Recommended 800x1280, ≤ 500 KiB. | |
| clockId | No | ||
| useCurrentDisplayClock | No | ||
| filePartName | No | Second multipart part name. Default is current UTC ms timestamp. | |
| fileName | No | Filename in multipart header. Defaults to basename(imagePath). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavioral traits. It accurately describes the mutation (replaces cached bitmap) and validation steps, but does not mention authentication requirements, potential side effects (e.g., whether the device restarts), or the response format. The description partially covers transparency but leaves gaps.
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 description is a single, dense paragraph that front-loads the core purpose and constraints. It efficiently conveys technical details without unnecessary words, but could be structured into bullet points for clarity. It earns its place with every sentence, achieving conciseness.
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?
Given the tool has 6 parameters, an optional target object, and no output schema, the description covers the main validation rules and multipart behavior but omits explanation for clockId and useCurrentDisplayClock. It also lacks return value information. The description is fairly complete for the core behavior but misses some contextual details.
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 67%, and the description adds value by explaining file validation and multipart framing beyond the schema. However, it does not clarify the meaning of clockId or useCurrentDisplayClock, which remain undocumented. The description compensates somewhat but not fully for the missing parameter details.
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 clearly states the tool replaces the cached dial bitmap via POST, and explicitly distinguishes itself from siblings by noting it does not modify DeviceImageUrl and does not accept tar.gz. It also specifies the targeted resource (clock dial background) and the HTTP method, leaving no ambiguity about its function.
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 provides file validation details (JPEG/WebP, ≤500 KiB, recommended 800x1280) but does not explicitly state when to use this tool vs alternatives like watchface_upload_file or watchface_patch_local. It implies context for replacing a dial background without changing the rest of the watchface, but lacks direct when-to-use or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Call Device/ResetLocalClockFromServer. This deletes local sys-side files before optional cloud refresh.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. | |
| clockId | Yes | ||
| parentClockId | No | ||
| parentItemId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that it deletes local files and optionally refreshes from cloud, but lacks details on consequences, permissions, or how the 'optional' aspect is controlled. No annotations to supplement.
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 concise sentences front-load the core action with no waste.
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?
Given 4 parameters, no output schema, and no annotations, the description is incomplete. It lacks return value info, error handling, and clarification on cloud refresh behavior.
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?
The description does not explain any parameters; only the clockId is implied. With low schema coverage (25%), the description should add meaning but does not.
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 clearly states the tool resets the local clock from server, deleting local sys-side files and optionally refreshing from cloud. This distinguishes it from siblings like watchface_create_local_clock.
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 implies usage for resetting a clock, but does not explicitly state when to use this vs alternatives. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Call Channel/SetBrightness with Brightness.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. | |
| brightness | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It does not mention that this is a write operation, possible side effects (e.g., changing brightness on a watchface), or any required permissions. The description is too minimal.
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 description is very concise (one short sentence), but it sacrifices clarity. It is front-loaded but does not effectively communicate purpose or behavior.
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?
Given the tool has a nested parameter (target) and no output schema, the description is incomplete. It should explain the effect of setting brightness, any constraints, or return behavior. Currently, it leaves major gaps.
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 50% due to the 'brightness' parameter lacking description. The description adds no meaning for 'brightness' beyond what the schema provides. The 'target' parameter is already described in the schema, so the description offers no additional value.
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 'Call Channel/SetBrightness with Brightness' is vague and does not clearly state what the tool does. It repeats the name without explaining the action in user-understandable terms. It fails to distinguish from sibling tools like watchface_get_brightness.
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?
No guidance is provided on when to use this tool versus alternatives. The sibling tools include a get counterpart, but the description does not specify that this is a set operation or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Call Channel/SetClockSelectId with ClockId.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. | |
| clockId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavior. It only states the API call, with no mention of effects, side effects, or requirements. This is insufficient.
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?
It is short but lacks structure and essential information. Under-specification is not conciseness; it fails to efficiently convey necessary details.
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?
The description is extremely brief and omits crucial context for a tool with a nested object parameter and no output schema. It does not explain the return value, behavior, or parameter constraints.
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?
The description only mentions 'ClockId' but adds no meaning beyond the schema. The clockId parameter has no description in the schema, and the description does not clarify it. Schema coverage is 50% but the description adds no value.
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?
Description is vague: 'Call Channel/SetClockSelectId with ClockId.' It restates the tool name but doesn't explain what selecting a clock means in context, leaving the purpose unclear.
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?
No guidance on when to use this tool versus siblings. The description provides no context about its applicability or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the curated template library (divoom://templates/curated): ~20 marketplace-derived watchface skeletons with tags such as weather, lunar_calendar, split_time_digits, pixel_theme, asset_heavy. Prefer cloning an existing ItemList layout before inventing raw coordinates. Filters support tagsAll/tagsAny, bucket, clockIds, item-count bounds, and dispPresent (template must include that disp id). Set includeWatchface=false for a compact summary without the full ItemList payload.
| Name | Required | Description | Default |
|---|---|---|---|
| tagsAll | No | Template must contain every listed tag (AND semantics). | |
| tagsAny | No | Template must contain at least one listed tag (OR semantics). | |
| bucket | No | Pick list bucket label from the curated generator (e.g. split_time_digits, weather, pixel_theme). | |
| clockIds | No | Restrict to explicit ClockId values. | |
| minItems | No | Minimum ItemList row count. | |
| maxItems | No | Maximum ItemList row count. | |
| dispPresent | No | Keep templates that already contain at least one row with this disp id. | |
| nameContains | No | Case-insensitive substring match on NameCn or NameEn. | |
| limit | No | Max templates to return (default 8, max 25). | |
| includeWatchface | No | If false, omit the nested watchface.ItemList payload (default true). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears the full burden. It clearly indicates the tool performs a search (implies read-only), describes filter behavior (AND/OR semantics), and mentions the output impact of includeWatchface. It does not cover error cases or pagination, but the core behavior is transparent.
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 description is a single, well-structured paragraph that front-loads the main purpose. Every sentence adds value: source, size, tags, best practice, parameter hints, and a usage tip. No wasted words.
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?
Given the complexity (10 parameters, no output schema), the description covers the library source, typical use cases, and parameter interactions. It lacks explicit mention of the output structure beyond the note about includeWatchface, but the context is otherwise sufficient for an agent to use the tool correctly.
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?
All 10 parameters have descriptions in the schema (100% coverage), so baseline is 3. The description adds value by explaining the curated library context, providing example tags, and advising when to use filters (e.g., dispPresent). This extra context elevates the score above baseline.
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 starts with a specific verb ('Search') and a clear resource ('curated template library'). It identifies the source path, mentions the ~20 templates and example tags, and distinguishes itself from sibling creation tools by advising to prefer cloning an existing layout over inventing coordinates.
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 explains when to use this tool (searching the template library) and provides guidance on filters, the includeWatchface flag, and best practices ('Prefer cloning...'). However, it does not explicitly state when not to use it or mention alternative tools for similar tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
POST /upload with multipart. First JSON part is caller-provided metadata (product-specific Command). 传输文件打包要求：固件在 divoom_http_server_upload_get_file_info 中要求每个文件段必须有 Content-Length，而浏览器 FormData 通常只使用 boundary 分隔、不包含每段 Content-Length。正在实现固件在无 Content-Length 时用 boundary 终止解析，并修复 JSON 段之后定位文件数据的指针计算；编辑器侧改为手动构造带 Content-Length 的 multipart 以提高兼容性。This server builds multipart with per-part Content-Length.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No | Optional per-call target override. If omitted, environment variables are used. | |
| filePath | Yes | ||
| metadata | Yes | ||
| filePartName | No | Second multipart part name. Default is current UTC ms timestamp. | |
| fileName | No | Filename in multipart header. Defaults to basename(filePath). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must carry the full burden. It mentions multipart handling and firmware compatibility but fails to disclose important traits like authentication requirements, error behavior, or side effects of uploading.
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 description is long and includes a large Chinese block that is irrelevant to an AI agent trying to use the tool. It lacks conciseness and buries the key action in technical details.
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?
Given the tool has 5 parameters (including nested objects) and no output schema, the description is incomplete. It does not explain return values, error cases, or how to construct the metadata parameter, leaving significant gaps for an agent.
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 60%, so the baseline is 3. The description adds minimal value beyond the schema, only hinting that metadata is a 'product-specific Command' but not explaining the structure or constraints of filePath, fileName, etc.
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 is overly technical, starting with 'POST /upload with multipart' and includes a large Chinese block about firmware internals, but does not clearly state that the tool uploads a file to a device. An AI agent would struggle to infer the core purpose.
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?
No explicit guidance on when to use this tool versus siblings like watchface_patch_local or watchface_replace_dial_bg_file. No prerequisites or conditions for use are provided.
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. Dates show when Glama detected each change.
v0.1.6watchface_create_local_clockwatchface_disp_catalogwatchface_font_catalogwatchface_get_brightnesswatchface_get_fonts_localwatchface_get_localwatchface_get_store_market_listwatchface_layout_suggestwatchface_onoff_screenwatchface_patch_localwatchface_protocol_quick_referencewatchface_raw_commandwatchface_replace_dial_bg_filewatchface_reset_local_then_cloudwatchface_set_brightnesswatchface_set_clock_selectwatchface_template_searchwatchface_upload_fileEach tool targets a distinct operation (create, patch, get, set, search, upload, etc.) with clear boundaries. Even similar tools like watchface_create_local_clock and watchface_patch_local differ in purpose (new vs modify). No two tools appear to do the same thing.
All tools share the consistent prefix 'watchface_' followed by a verb_noun pattern (e.g., create_local_clock, get_fonts_local, replace_dial_bg_file). Minor multi-word phrases like 'reset_local_then_cloud' still follow the pattern without mixing styles.
18 tools is well-scoped for a specialized watchface management server. Each tool addresses a specific need (creation, patching, brightness, fonts, templates, raw commands, etc.) without redundancy or bloat.
The tool set covers most lifecycle operations (create, read, update, delete via reset) plus utilities for fonts, templates, brightness, and screen control. A minor gap is lack of a dedicated 'delete single clock' tool, but the reset function covers it.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Manage digital signage screens, playlists and media from your AI assistant.
Control your Tesla from your AI assistant - climate, charging, access, and security.
Create, test, publish, and manage Dreamlit notification workflows from AI clients.
Control Android TV from any AI. 38 MCP tools: playback, recap, recommend, smart-home, schedules.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/DivoomDevelop/mcp-divoom-lan'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
