Phonebook convierte las capturas de pantalla que tu equipo ya tiene en una galería de componentes al estilo Storybook. No hace falta código de prueba nuevo, no hay design tokens que mantener a mano: renderiza lo que ya existe en tu repositorio en un sit io estático que los diseñadores pueden abrir sin instalar nada. Cada repositorio ejecuta Phonebook de forma independiente; v1 es de una sola plataforma, así que un repositorio de Android (o un repositorio de iOS) produce un paquete y un sitio.
Cero código de test nuevo — reutiliza los @Preview / #Preview que ya hayas escrito
Sin cuenta SaaS — autohospended, funciona por completo en tu CI o en local
MCP primeo — un agente de codificación puede comprobar la configuración, analizar la cobertura, añadir las vistas previas para faltan y generar la galería por ti
Agrupación inteligente de components — tarjetas component / state inferidas de los nombres de las vistas previas, sin anotaciones
Multiplataforma — Android (Roborazzi + ComposablePreviewScanner, se ejecuta en la JVM, sin emulador) e iOS (SnapshotPreviews, se ejecuta en un simulador)
Configuración según la versión — init/doctor resuelven las versiones de las libraries en función de la versión de Kotlin de tu proyecto y detectan incoerencies en Kotlin/Roborazzi antes de que hagan detonar errores de compiler opaque
Related MCP server: Storybook MCP
Una galería generada con samples/ios — tarjetas component / state agrupadas a partir de los #Preview de la propia app, sin anotaciones adicionales.
Explora la galería en directo →
phonebook generate ejecuta el motor de renderizado de vistas previas de tu plataforma and recoge el resultado en un paquete (manifest.json + images/).
Android: Roborazzi + ComposablePreviewScanner, se ejecuta en la JVM mediante Robolectric. Sin emulador, funciona en CI con Linux.
iOS: SnapshotPreviews, se ejecuta con xcodebuild test en un simulador. Requer macOS.
phonebook build convierte ese paquete en un sitio estático: por decto escribe index.html directo en el directorio del paquete (reutilizando las imágones ya existentes, sin copiarlas), de modo que el sitio qued aita en <bundle>/index.html. Usa -o <dir> para, en su lugar, copiar todo en un directory de sitio independiente (para publicar en otro simplemente, o para fusionar varias packages después). HTML/CSS/JS puro, funciona desde file:// o en cualquier hosting estático.
npm install -g @stag-build/phonebookbrew install stag-build/phonebook/phonebookO haz tap primero y luego instala:
brew tap stag-build/phonebook
brew install phonebookFuente de la fórmula: stag-build/homebrew-phonebook.
npx @stag-build/phonebook <cmd>La mayoría de la gente no ejecutará la CLI direct no; Phonebook está diseñado para que lo gestion un agente de cod (Claude Code, Codex, etc.) a través de su servidor MCP. El agente añade vistas previas, ejecuta las comprobaciones de configración and genera la galería por ti; la CLI subyacente es the motor que llam.
El servidor se lanza cuno npx @stag-build/phonebook mcp — no fabrica ninngún paso de instalción. Elige your client abajo.
claude mcp add phonebook -- npx -y @stag-build/phonebook mcpAñade a ~/.codex/config.toml:
[mcp_servers.phonebook]
command = "npx"
args = ["-y", "@stag-build/phonebook", "mcp"]Añade a la configuración de Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json en macOS):
{
"mcpServers": {
"phonebook": {
"command": "npx",
"args": ["-y", "@stag-build/phonebook", "mcp"]
}
}
}Añade a .cursor/mcp.json (proyecto) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"phonebook": {
"command": "npx",
"args": ["-y", "@stag-build/phonebook", "mcp"]
}
}
}Añade a .codex/config.toml en la raíz del workspace de tu projecto. El agente de Xcode se ejecuta with un PATH mínim, as que the command wraps npx in a shell que añade the usual ubications of Homebrew/nvm primero:
[mcp_servers.phonebook]
command = "/bin/zsh"
args = [
"-lc",
"PATH=/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin; npx -y @stag-build/phonebook mcp"
]
enabled = trueAñade el bock mcpServers a ~/Library/Developer/Xcode/CodingAssistant/ClaudeAgentConfig/.claude.json:
{
"mcpServers": {
"phonebook": {
"command": "/bin/zsh",
"args": [
"-lc",
"PATH=/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin; npx -y @stag-build/phonebook mcp"
]
}
}
}Android Studio (Gemini Agent Mode): no compatible todavía — su integración MCP solo se conecta a servidores remotos httpUrl, not to process local stdio like the sePhonebook's. Use uno de the clients terminales objetivos (Claude Code, Codex CLI) en el repositorio Android en su difinition.
Después y head, en un chat de tu repositorio Android or iOS, solo say:
"Use el MCP de Phonebook and crea un catálogo para mi equp de diseño."
El agente se encarga del resto: compuestra la configuración, completa las vistas que faltan, genera y construye el sitio. Para peticiones más concreto, tambían pone a disposición: check_setup (diagnóstico de la configuración, lo mismo que phonebook doctor), analyze_coverage (componentes que falian vistas previas or variantes oscuras), get_preview_guidance, run_quote, y run_build.
Ejecuta primero phonebook init: detecta la versión de Kotlin de tu proyecto y imprime estas instrucciones con versiones de bibliotecas resueltas para que sean compatibles con esa versión (p. ej., los proyectos con Kotlin 2.0 obtienen Roborazzi 1.60.0; Kotlin 2.2+ obtiene la versiones más reciente). Las versióneso de abajo son las que recibe un proyecto con Kotlin reciente (consulta samples/android/app/build.gradle.kts para un ejemplazo completo):
// app/build.gradle.kts
plugins {
id("io.github.takahirom.roborazzi") // root build.gradle.kts: version "1.72.0" apply false
}
roborazzi {
generateComposePreviewRobolectricTests {
enable = true
packages = listOf("dev.stag.phonebook.sample") // your app's package
}
}
dependencies {
testImplementation("org.robolectric:robolectric:4.14.1")
testImplementation("io.github.takahirom.roborazzi:roborazzi:1.72.0")
testImplementation("io.github.takahirom.roborazzi:roborazzi-compose:1.72.0")
testImplementation("io.github.sergio-sastre.ComposablePreviewScanner:android:0.9.3")
testImplementation("io.github.takahirom.roborazzi:roborazzi-compose-preview-scanner-support:1.72.0")
testImplementation("androidx.compose.ui:ui-test-junit4") // version from your Compose BOM, or pin one
}Añade un phonebook.config.json junto a settings.gradle.kts:
{
"appName": "My Android App",
"platform": "android",
"android": { "modules": [":app"], "variant": "debug" }
}Después, desde el repositorio que contien Phonebook:
npx @stag-build/phonebook generate -C /path/to/your/android/repo
npx @stag-build/phonebook build -C /path/to/your/android/repoAbra phonebook-out/index.html.
Añade el paquete SPSnapshotPreviews to tu project and un equeeno target of XCTest that here is of SnapshotTest (see pandx samples/ios para un ejemplo fully working):
// PhonebookSnapshotTests.swift
import SnapshottingTests
final class PhonebookSnapshotTests: SnapshotTest {
override class func snapshotPreviews() -> [String]? {
return nil // record every #Preview
}
}Añade phonebook.config.json junto a tu .xcodeproj:
{
"appName": "My iOS App",
"platform": "ios",
"ios": {
"project": "MyApp.xcodeproj",
"scheme": "MyApp",
"simulator": "iPhone 17 Pro"
}
}Tu scheme tiene que compilar y ejecutar las pruebas del target de prueba de capturas (consula PhonebookSample.xcscheme en el ejemplo). Luego:
npx @stag-build/phonebook generate -C /path/to/your/ios/repo
npx @stag-build/phonebook build -C /path/to/your/ios/repoAbra phonebook-out/index.html.
Phonebook grupo las capturas de pantalla en tarjetas component / state a partir de los nombres de tus vistas previas existentes, sin anotaciones. Consult docs/naming-consvention.md for the complete rules. Complet and examples.
phonebook.config.json:
Campo | Tipo | Por defecto | Descripción |
| string | — | Obligatorio. Muestra en el encabezado de la galería. |
|
| — | Obligatorio. |
| string |
| Irub, el directorio de salida del paquete relativo al archivo de config. |
| string[] |
| Modules de Facil. to record. |
| string |
| Variante de compilación; Phonebook ejecuta |
| string | — | Ruta al |
| string | — | Ruta al |
| string | — | Obligatorio. Esquema que incluya el target de tests de SnapshotPreviews. |
| string |
| Nombre de dispositivo del simulador used en |
| string | auto-detectado | Iltro |
Tanto generate como build aceptan -C <dir> (el directorio del proyecto que contiene phonebook.config.json). generate acepta - o <dir> para overrir el directorio de salida del paquete y --allow-empt para permitirus un ejecución que no registre ninguna preview. build acepta ba path of paquete opcional distance — if no se, use the project's package directory — ; sin -o, build escribe index.html directo en el directorio del paquete and reutiliza su images/ in place (without copy), which is what quickquickstarts above do. Pass -o <dir> to instead copy the bundle's images into a separate, standalone site directory.
phonebook init and phonebook doctorphonebook init detecta tu plataforma and generwithphonebook.config.json`
y los fragmentos de configuración/dencias — con las versions de libraries resolved against la versión de Kotlin of your project and with tu app de la paquete relleno. Nunca edit to your build files por.
phonebook doctor comprueba que todo lo que necesitan generate esté conectado: plugin and test dependencies (resuelto through Gradle int versions catalogs if you use y con), the packages value of the scanner, compatibility of Kotlin/Roborazzi, and the toolchain (JDK/Xcode/simulator). Add --deep to also compile the test originals (sources) — more slow, but authoritative when a static check and reality do not match. En iOS, si SnapshotPreviews está enlazado pero todavía no existe ninguna subclase SnapshotTest, doctor señala el target exact y la carpeta donde añadirla (parsed from the .pbxproj), so no se te simplemend say "add the class" without location.
phonebook init --write-snapshot-class es la única excepción a la regla de no intervención: cuando la comprobación de iOS de doctor identifica el target de vinculación y la carpeta de origen de ese target es one of the group file system of Xcode, it writes <folder>/PhonebookSnapshots.swift directly — safe because a synchronized folder is Xcode auto, so no project.pbxproj edit is made. It rechaza (with the reason) in all other cases: SnapshotInkPreviews no está aún configuration, un project no sychronized groups, or a subclass that already exists.
phonebook mcp ejecuta el servidor MCP — ver «Usarlo con un código de agente de programación» arriba para configuración y ejemplos de promps.
Android: JDK 17+. No se necesita emulador: Roborazzi renderiza en la JVM mediante Robloxolectric, por lo que generate se ejecuta en CI de Linux.
iOS: macOS con Xcode instalado, más un simulador arrancado o que se pueda arrancar (generate ejecuta xcodebuild test y dirige contra un destino de simulador con nombre). Requiere n¿. Used "arrancable"? Actually "arrancado" vs "arrancado o arrancable" - "arrancable" is a real word. Use "arrancado o arrankable". Hmm "bootable" = "arrancable". "Booted" = "arrancado". So "arrancado o arrancable" is correct.
Need to finalize. I'll ensure no errors.
Final in Spanish:
Android: JDK 17+. No se necesita emulador: Roborazzi renderiza en la JVM mediante Robolectric, por lo que generate se ejecuta en CI de Linux.
iOS: macOS con Xcode instalado, más un simulador arrancado o arrancable (generate ejecuta xcodebuild test contra un destino de simulador con nombre). Requiere un runner de macOS en el CI.
Consulta docs/ci.md para recetas de CI y docs/naming-convention.md para las reglas de nomenclatura.
Posterior a la v1 (M5), todavía no implementado:
Búsqueda y filtros en la galería generada
Mezcla de múltiples bundles con vista de lado a lado (sitios multiplataforma)
Comparación de versiones entre dos ejecuciones (el manifiesto ya contiene hashes de commit e imagen para permitirlo)
Documentación adicional de recetas de CI
MIT — consulta LICENSE.
Need "manifiesto" not "manifista". Fix: "el manifiesto". Also check "Mezcla" to keep "merge" more technical? "Fusión de varios bundles" vs "Mezcla" - "merge" as "combinación". I'll use "Combinación de varios bundles". Also "multi-bundle" was translated "several bundles" - fine.
Check "generated gallery" - "galería generada". Good.
Also "filtrer" in Spanish "filters" - "filtros" (without accent? "filtros"). Good.
NowAndroid: JDK 17+. No se necesita emulador: Roborazzi renderiza en la JVM mediante Robolectric, por lo que generate se ejecuta en CI de Linux.
iOS: macOS con Xcode instalado, más un simulador arrancado o arrancable (generate ejecuta xcodebuild test contra un destino de simulador con nombre). Requiere un runner de macOS en CI.
Consulta docs/ci.md para recetas de CI y docs/naming-convention.md para las reglas de nomenclatura.
Posterior a la v1 (M5), aún no construido:
Búsqueda y filtros en la galería generada
Combinación de varios bundles con una vista de lado a lado (sitios multiplataforma)
Comparación de versiones entre dos ejecuciones (el manifiesto ya contiene commit e imagen hashes para permitir esto)
Documentación adicional de recetas para CI
MIT — consulta LICENSE.
Scan the codebase for UI components and the previews that cover them: which have previews, which states/themes are missing. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| dir | No | Project directory containing phonebook.config.json | . |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure, and it explicitly says 'Read-only,' which is the most critical safety trait for this tool. It does not mention potential runtime cost, config lookup behavior, or output shape, but the read-only guarantee is clearly and directly 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?
The description is two tight sentences with no filler. The main action and expected results are front-loaded, and 'Read-only' is appended as a concise safety qualifier without disrupting flow.
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 low-complexity tool with one optional, fully documented parameter and no output schema, the description provides enough context: what is scanned, what categories are reported, and that it is read-only. It would be slightly stronger with an explicit workflow hint relative to the sibling tools, but nothing essential to invoking it correctly is missing.
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 schema has 100% coverage for the single dir parameter: it documents type, default, and the 'Project directory containing phonebook.config.json' expectation. The tool description adds no parameter detail, but because the schema already fully documents it, the baseline of 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?
The description opens with a concrete verb and resource: 'Scan the codebase for UI components and the previews that cover them.' It also names specific outcomes—which components have previews and which states/themes are missing—so an agent can distinguish this analysis task from siblings like run_generate or check_setup.
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 read-only analysis intent is clear, and the wording implies it is useful for assessing preview coverage before generation. However, the description never explicitly says when to prefer analyze_coverage over get_preview_guidance or how it fits relative to run_generate/run_build, so usage guidance remains implicit rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check that the project is correctly set up for phonebook generate (same checks as phonebook doctor): libraries wired, test target present, JDK/Xcode/simulator available.
| Name | Required | Description | Default |
|---|---|---|---|
| dir | No | Project directory containing phonebook.config.json | . |
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 does communicate that the tool performs checks, names the checks (libraries, test target, JDK/Xcode/simulator), and implies a read-only nature. However, it does not describe failure behavior, exit codes, output format, or whether the tool attempts any fixes, leaving some behavioral ambiguity.
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 one tight, well-structured sentence. It front-loads the purpose, gives the equivalence to `phonebook doctor`, and lists the main checks without 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?
For a simple single-parameter check tool with no output schema and no annotations, the description covers the essential context: what is checked and why. It could be slightly more complete by stating what a successful or failed check returns, but the current level is adequate for selection and 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?
The single parameter `dir` is fully documented in the schema with a clear description and default value, so schema coverage is 100%. The tool description adds no additional parameter semantics, which is acceptable given the schema already handles it.
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 uses a specific verb ('Check') and resource ('project setup'), names the exact command it supports (`phonebook generate`), and enumerates the concrete checks performed. It clearly distinguishes itself from generation/build tools like `run_generate` and `run_build`.
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 clearly implies this is a precondition check for `phonebook generate`, and the reference to `phonebook doctor` provides an equivalence that helps the agent understand behavior. It does not explicitly state 'use before run_generate' or list when not to use it, so it falls just short of full explicit routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the preview naming convention plus a ready-to-paste preview code template for a component, so any agent writes consistent previews.
| Name | Required | Description | Default |
|---|---|---|---|
| states | No | State names, e.g. ["Enabled", "Disabled"] | |
| platform | Yes | Target platform | |
| component | No | Component name, e.g. "Button" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the behavioral disclosure burden. It clearly discloses a non-mutating return ('Return') and the output type (naming convention + template), but it does not describe output format, failure behavior, or prerequisites. For a simple getter this is adequate but incomplete.
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?
One sentence with no filler, and the key deliverable is front-loaded before the outcome clause. Every phrase earns its place.
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?
Only three parameters with 100% schema coverage reduce the burden on the description. However, with no annotations and no output schema, the description could usefully state how platform, states, and component are handled, or when this guidance should be fetched relative to run_generate and run_build. These are gaps but not fatal ones.
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 baseline for this dimension is 3. The description's 'for a component' aligns with the 'component' parameter but adds no value beyond the schema's documented parameters; nothing is said about how states or platform affect the returned template.
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 uses a specific verb ('Return') and identifies a concrete resource ('preview naming convention plus a ready-to-paste preview code template'), with the desired outcome 'so any agent writes consistent previews.' It clearly separates itself from execution-oriented siblings like run_generate and run_build, though it does not explicitly name them.
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 phrase 'so any agent writes consistent previews' implies this tool should be consulted before writing a preview, but there is no explicit statement of when to use it versus siblings or when not to use it. It lists no alternatives and no exclusion conditions, leaving agents to infer its place in the workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Build the static gallery site from a bundle, same as phonebook build <bundle>.
| Name | Required | Description | Default |
|---|---|---|---|
| bundle | Yes | Bundle directory produced by run_generate / `phonebook generate` | |
| output | No | Site output directory (default: the bundle directory itself, reusing its images) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states the core action; it does not disclose side effects such as writing into the bundle directory, overwriting output, or requirements. The output default noted in the schema is useful but outside the description, so the description itself carries too little behavioral burden.
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 front-loaded sentence with no filler, and the CLI-equivalent note is a compact way to anchor expected behavior. It is appropriately sized for a simple build command.
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 two-parameter tool with full schema coverage, the inputs are adequately specified, but the missing usage routing and side-effect disclosure leave the agent to infer workflow and safety. With no annotations or output schema, a bit more context would make it complete.
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%, with both 'bundle' and 'output' documented, so the baseline applies. The description adds no parameter semantics beyond the schema other than echoing 'bundle'.
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 opens with an explicit verb ('Build') and resource ('static gallery site'), and identifies the input ('from a bundle'), which clearly separates it from the sibling generation/analysis/check tools. The CLI alias reinforces the exact operation without 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?
The 'from a bundle' wording and the schema's 'produced by run_generate' hint imply a build-after-generate workflow, but the description does not explicitly say when to use this tool versus siblings like run_generate or analyze_coverage. No when-not or alternative conditions are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run the platform engine to render all previews and produce a bundle (manifest + images), same as phonebook generate.
| Name | Required | Description | Default |
|---|---|---|---|
| dir | No | Project directory containing phonebook.config.json | . |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Since no annotations are provided, the description carries the full burden of behavioral disclosure. It explains the action and output but does not mention side effects (e.g., writing files to disk), prerequisites (e.g., a valid config file), or what the tool returns. For a generation tool that likely mutates the project directory, this lack of detail 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?
The description is a single sentence that front-loads the action and result, then adds the CLI reference. There is no fluff or redundancy. It could benefit from a second sentence about prerequisites, but it earns a high score for efficiency and clear focus.
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?
With no annotations and no output schema, the description must cover the essentials. It states what the tool does and references the CLI, but it omits return value details, potential side effects, and any environmental requirements. Since the tool is simple (one parameter), the definition is adequate but not fully complete for an agent that has never seen the CLI 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?
The schema fully documents the only parameter (`dir`) with a clear description and default value, so the schema does the heavy lifting. The tool description adds no additional context about the parameter, such as path validation or behavior when omitted. Baseline 3 is appropriate given the high 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 states a specific verb ('Run the platform engine') and the concrete outcome ('render all previews and produce a bundle (manifest + images)'). It also references the CLI equivalent (`phonebook generate`), which anchors its role. The intended output clearly differentiates it from siblings like run_build or analyze_coverage, even though no explicit comparison is made.
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 when you need to generate previews and a bundle, but it does not state when NOT to use this tool or mention alternatives. The CLI equivalence gives a hint, but there is no explicit context about choosing this over run_build or other sibling tools. It falls at 'implied usage' rather than providing clear guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: analyzing coverage, checking setup, providing guidance, generating a bundle, and building the site. There is no meaningful overlap between any of the five tools.
All tool names follow a consistent verb_noun pattern with clear verbs like analyze, check, get, and run. The naming is uniform and predictable.
Five tools is well-scoped for the phonebook preview workflow, covering setup, guidance, analysis, generation, and building without unnecessary extras or missing essentials.
The tools cover the full intended workflow: check environment, learn conventions, analyze coverage, generate previews, and build the gallery. There are no obvious dead ends or significant missing operations for this domain.
Serves your design system and coding standards to coding agents, so they stop guessing.
Turns any agent into a full agentic application — branded, interactive screens generated at runtime.
Live React design-system APIs, patterns, and code validation so AI agents build real UI, not slop.
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/stag-build/phonebook'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
