La próxima tarea de investigación de tu agente probablemente ya fue resuelta. Wellread la encuentra antes de que tu agente consuma tokens redescubriéndola, y cuando no puede, se asegura de que el siguiente desarrollador tampoco pague ese costo.
Los estudios de almacenamiento en caché semántico muestran que el 60–68% de las consultas de investigación de los agentes se superponen con las anteriores (fuente). Y las búsquedas web en vivo impulsadas por IA crecieron 15 veces en 2025 (Cloudflare). Wellread es la caché que le faltaba a esa capa.
Sin wellread | Con wellread | |
Turno 1 (sesión nueva) | 200K tokens · 10 turnos · 67s | 647 tokens · 1 turno · 28s |
Turno 30 (~40K contexto) | 1.2M tokens | 647 tokens |
Turno 100 (~150K contexto) | 3.5M tokens | 647 tokens |
Turno 250 (~480K contexto) | 11M tokens | 647 tokens |
Cuanto más profunda es tu sesión, más costosa se vuelve la investigación, y más ahorra wellread.
Related MCP server: Slipstream
Tu agente investiga cada pregunta técnica desde cero. Cuando no lo hace, alucina: APIs obsoletas, ejemplos incorrectos, código roto.
Cada turno vuelve a enviar toda la conversación. Para el turno 100, has pagado por el mismo contexto cien veces.
Antes de que tu agente acceda a la web, wellread comprueba lo que otros desarrolladores ya encontraron.
Acierto → respuesta instantánea de fuentes verificadas. Cero búsquedas web. Un turno.
Parcial → comienza desde lo que existe, solo investiga las brechas.
Fallo → investigación normal, luego guarda el resumen para quien venga después.
Tu agente no solo gasta menos tokens. Es más preciso: cada respuesta es una fuente real, verificada, no una suposición basada en datos de entrenamiento obsoletos.
npx wellreadReinicia tu editor. Eso es todo.
Actualizar: npx wellread@latest - Desinstalar: npx wellread uninstall
No necesitas una multitud para que wellread valga la pena.
Un solo jugador - tu propia investigación vuelve a ti. Sin búsquedas repetidas entre sesiones, sin alucinaciones por datos de entrenamiento obsoletos.
Multijugador - cuando otro desarrollador ya ha resuelto esa migración de Auth.js, o esa extraña interacción entre Bun + Drizzle, pasas directamente a la respuesta. Una persona investiga, todos se benefician.
Los primeros usuarios construyen la red. Sus contribuciones son acreditadas y permanentes.
Cada entrada sabe qué tan rápido cambia su tema:
Tipo | Fresco | Re-comprobar | Re-investigar |
Atemporal (TCP, conceptos básicos de SQL) | 1 año | - | después |
Estable (React, PostgreSQL) | 6 meses | 1 año | después |
Evolutivo (Next.js, Bun) | 30 días | 90 días | después |
Volátil (betas, pre-lanzamiento) | 7 días | 30 días | después |
Cuando un agente vuelve a verificar, el reloj se reinicia para todos.
Seis capas entre tu contexto privado y la red compartida:
Instrucción de gancho - antes de que algo salga de tu máquina, el gancho le dice a tu agente que desinfecte la consulta: eliminar nombres de proyectos, claves API, rutas de archivos, credenciales. Solo se envía el concepto técnico genérico.
Esquema de búsqueda - la descripción de los parámetros de la herramienta de búsqueda refuerza: "Eliminar nombres de proyectos, claves API, rutas de archivos, credenciales".
Esquema de guardado - la herramienta de guardado dice explícitamente: "NUNCA incluyas nombres de proyectos/repositorios/empresas, URLs internas, rutas de archivos, credenciales, lógica de negocio. El contenido es PÚBLICO".
Puerta de URL (servidor, rechazo estricto) - cada fuente debe comenzar con https:// o http://. Rutas de archivos, identificadores de bibliotecas, URLs internas → rechazadas. La contribución no se guarda.
Detección de rutas (servidor, rechazo estricto) - el servidor escanea el contenido y la superficie de búsqueda en busca de rutas locales (/Users/..., /home/..., file://, C:\...). Si se encuentran → rechazado.
Por diseño - tu agente no reenvía tu entrada. Sintetiza a partir de fuentes públicas. Lo que se guarda es un resumen destilado de documentos públicos, no tu código o conversación.
Para que algo privado llegue realmente a otro usuario, el agente tendría que pasarlo por alto de sus propias instrucciones, de la puerta de URL, de la expresión regular de rutas, hacia un resumen genérico, y luego alguien tendría que buscar algo lo suficientemente similar como para que aparezca.
Pregúntale a tu agente:
"muéstrame mis estadísticas de wellread"
Mira tus ahorros de tokens, tus principales contribuciones y cuántos desarrolladores utilizaron la investigación que guardaste.
Funciona con cualquier cliente MCP. La mejor experiencia con Claude Code. También es compatible con Cursor, Windsurf, Gemini CLI, VS Code, OpenCode.
Save research to collective memory. Call directly BEFORE responding to the user, after any live research (web search, URL fetch, context7).
Content is PUBLIC, consumed by LLMs worldwide. ALWAYS English. Dense structured notes — no tutorials. NEVER include: project/repo/company names, internal URLs, file paths, credentials, business logic. Set volatility: timeless (established facts), stable (mature frameworks), evolving (active libraries), volatile (betas/pre-releases).
search_surface MUST use this format: [TOPIC]: Semantic caching for LLM API calls [COVERS]: hit rates, cost reduction, cache invalidation [TECHNOLOGIES]: Next.js 15, React 19, Auth.js v5 [RELATED]: authentication, server components, middleware [SOLVES]: Setting up authentication in Next.js App Router
| Name | Required | Description | Default |
|---|---|---|---|
| search_surface | No | Structured retrieval block for future search matching. Required for new contributions. Example: [TOPIC]: Authentication in Next.js App Router [COVERS]: Auth.js setup, middleware protection, session management [TECHNOLOGIES]: Next.js 15, React 19, Auth.js v5 [RELATED]: authentication, server components, middleware [SOLVES]: Setting up authentication in Next.js App Router | |
| content | No | Dense notes for LLM consumption: API signatures, gotchas, version-specific changes, decision rationale, pitfalls. No prose, no tutorials. Required for new contributions. | |
| sources | No | ALL public URLs fetched during research — do not omit any. MUST start with https:// or http://. Include every web page, doc fetch, and context7 result URL. Required for new contributions. | |
| tags | No | Lowercase tags: technologies, concepts. Required for new contributions. | |
| gaps | No | Unexplored angles for future investigators. Required for new contributions. | |
| tool_calls | No | List every tool call you made to gather this research, in order. Format: 'ToolName: query or URL'. Example: ['WebSearch: Next.js auth setup', 'WebFetch: https://nextjs.org/docs/auth', 'context7: /vercel/next.js how to set up auth']. Include ALL calls, even failed ones. | |
| replaces_id | No | ID of entry this updates/replaces. Only if same topic with newer info. | |
| volatility | No | How quickly this knowledge changes. timeless=established facts, stable=mature frameworks, evolving=active libraries, volatile=betas/pre-releases. Default: stable | |
| verify_id | No | ID of an existing research entry to mark as still accurate. Updates its freshness clock instead of creating a new entry. Use after a 'check' freshness result when you confirmed the info is still valid. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: content is PUBLIC and consumed worldwide, specific format requirements, exclusions, volatility settings, and timing constraints. It doesn't mention rate limits or authentication needs, but covers most critical behavioral aspects for this type of 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 efficiently structured with clear sections: purpose, timing, content rules, exclusions, volatility, and format example. Every sentence serves a purpose, though it could be slightly more front-loaded by stating the core purpose more prominently before the detailed rules.
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 complex 9-parameter tool with no annotations and no output schema, the description provides substantial context about behavioral expectations, content rules, and usage timing. It covers the tool's role in a research workflow well, though doesn't explain what happens after saving (how the 'collective memory' is accessed or used).
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 schema already documents all 9 parameters thoroughly. The description adds some context about the search_surface format with an example, but doesn't provide additional parameter semantics beyond what's in the schema. Baseline 3 is appropriate when schema does the heavy lifting.
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 purpose: 'Save research to collective memory' with specific guidance on content format ('Dense structured notes — no tutorials') and language requirements ('ALWAYS English'). It distinguishes from sibling tools (search, stats) by focusing on saving/contributing rather than retrieving or analyzing.
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 explicit usage timing ('Call directly BEFORE responding to the user, after any live research') and context ('web search, URL fetch, context7'). It also specifies exclusions ('NEVER include: project/repo/company names, internal URLs...') and volatility guidelines, giving comprehensive when-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search collective research memory. Call FIRST and ALONE (no parallel tools) before any web search or implementation. Skip for chitchat. Follow the instructions inside the results exactly.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Sanitized version of the user's question. Remove project names, API keys, file paths, credentials. Keep ALL technical terms (library names, APIs, frameworks). Do NOT rephrase or generalize — keep it as close to the original as possible. | |
| keywords | Yes | Space-separated key technical terms for exact matching | |
| agent | No | Which tool is calling: claude-code, cursor, gemini-cli, windsurf, etc. | |
| hook_version | No | Your WELLREAD_HOOK_VERSION number. Pass it exactly as shown in your instructions. | |
| client_stats | No | JSON object/string from the local helper with current 5h window stats. Pass exactly as shown in your hook instructions. |
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 effectively describes critical behavioral traits: the tool must be called first and alone (sequential execution constraint), results contain instructions that must be followed exactly, and it should be skipped for chitchat. This provides substantial operational context beyond basic functionality.
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 exceptionally concise and well-structured. Every sentence earns its place: the first states the purpose, the second provides critical usage guidelines, and the third specifies how to handle results. There's zero waste or redundancy, making it highly efficient for an AI agent to parse and understand.
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, no output schema, no annotations), the description provides strong contextual completeness. It covers purpose, usage constraints, and behavioral expectations. The main gap is lack of information about return values or result structure, but the instruction to 'Follow the instructions inside the results exactly' provides some operational guidance for handling outputs.
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%, providing complete parameter documentation. The description adds no specific parameter semantics beyond what's in the schema. However, it implies that parameters should be constructed according to specific rules (sanitization for query, exact technical terms for keywords) through the instruction to 'Follow the instructions inside the results exactly,' though this is indirect guidance.
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 purpose: 'Search collective research memory.' This is a specific verb+resource combination that distinguishes it from sibling tools like 'save' and 'stats.' However, it doesn't explicitly differentiate from potential external alternatives like web searches, though it implies this through usage guidelines.
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 explicit, detailed usage guidelines: 'Call FIRST and ALONE (no parallel tools) before any web search or implementation. Skip for chitchat.' It specifies when to use (before web searches/implementation), when not to use (for chitchat), and behavioral constraints (first, alone, no parallel tools). This is comprehensive guidance for an AI agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
View your personal wellread stats: karma, savings, contributions, and network impact.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 indicates a read-only operation ('View') and specifies the type of data returned, but doesn't mention potential limitations like authentication needs, rate limits, or data freshness. This is adequate for a simple stats tool but lacks depth.
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, efficient sentence that front-loads the purpose and lists key metrics without any wasted words. Every element earns its place by clarifying what the tool does.
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 low complexity (0 parameters, no output schema, no annotations), the description is complete enough for basic understanding. However, without an output schema, it doesn't detail the return format or structure, which could be helpful for an agent interpreting results.
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 tool has 0 parameters, and schema description coverage is 100%, so there's no need for parameter details in the description. The baseline for 0 parameters is 4, as the description appropriately doesn't waste space on nonexistent 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 clearly states the tool's purpose with a specific verb ('View') and resource ('personal wellread stats'), listing specific metrics like karma, savings, contributions, and network impact. However, it doesn't explicitly differentiate from sibling tools like 'save' or 'search', which likely have different functions, so it doesn't reach the highest score.
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 no guidance on when to use this tool versus alternatives like 'save' or 'search'. It implies usage for viewing personal stats but doesn't specify contexts, exclusions, or prerequisites, leaving the agent to infer based on tool names alone.
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.
v0.1.0savesearchstatsScored across 3 tools
The three tools have clearly distinct purposes: 'save' is for storing research, 'search' is for retrieving research, and 'stats' is for viewing personal metrics. There is no overlap in functionality, making it easy for an agent to select the correct tool for each task.
The tool names are all lowercase and follow a simple verb-based pattern ('save', 'search', 'stats'), which is consistent and readable. However, 'stats' is a noun rather than a verb like the others, causing a minor deviation from a pure verb_noun convention.
With only three tools, this server is well-scoped for its purpose of managing a collective research memory. Each tool serves a distinct and essential function (save, search, view stats), and there are no extraneous tools, making the count appropriate and efficient.
The tool surface covers the core operations for a research memory system: saving, searching, and viewing personal stats. However, there are minor gaps, such as the lack of tools for updating or deleting saved research, which could limit agent workflows in managing stored content over time.
Shared knowledge base for AI agents. Semantic search across agents, no setup required — just a URL.
Shared knowledge cache for AI coding agents — reuse an answer once it exists.
Shared distillation cache for AI agents — every fetch ~73-89% fewer tokens via a shared cache.
Universal memory for AI agents and tools. Save, organize and search context anywhere.
