██████╗ ██╗ ██████╗ ███████╗██╗ ███████╗ ██████╗ █████╗ ████████╗███████╗
██╔══██╗██║ ██╔══██╗██╔════╝██║ ██╔════╝██╔════╝ ██╔══██╗╚══██╔══╝██╔════╝
██████╔╝██║ ██║ ██║█████╗ ██║ █████╗ ██║ ███╗███████║ ██║ █████╗
██╔═══╝ ██║ ██║ ██║██╔══╝ ██║ ██╔══╝ ██║ ██║██╔══██║ ██║ ██╔══╝
██║ ██║ ██████╔╝███████╗███████╗███████╗╚██████╔╝██║ ██║ ██║ ███████╗
╚═╝ ╚═╝ ╚═════╝ ╚══════╝╚══════╝╚══════╝ ╚═════╝ ╚═╝ ╚═╝ ╚═╝ ╚══════╝
███╗ ███╗ ██████╗██████╗
████╗ ████║██╔════╝██╔══██╗
██╔████╔██║██║ ██████╔╝
██║╚██╔╝██║██║ ██╔═══╝
██║ ╚═╝ ██║╚██████╗██║
╚═╝ ╚═╝ ╚═════╝╚═╝
Servidor MCP que expone el agente de codificación pi como un trabajador delegable y dirigible.
Apunta Claude Code (o cualquier host MCP) hacia él y delega trabajo en cualquiera de los ~38 proveedores de pi (DeepSeek, Grok, GLM, Kimi, Qwen, Codex, OpenRouter, llama.cpp local) con el contexto del subagente manteniéndose fuera de tu conversación principal.
Tu arnés principal se ejecuta en un modelo caro, con una ventana de contexto que te importa. Mucho de lo que hace no necesita ese modelo, y daña activamente ese contexto: buscar en un repositorio cada punto de llamada, leer un archivo de 2000 líneas para responder una pregunta, auditar lo que dejó una refactorización.
Encomienda ese trabajo a un delegado en su lugar:
Coste. El trabajo pesado se ejecuta en DeepSeek, GLM, Kimi, Qwen o un llama.cpp local. Pagas precios de frontera solo por el razonamiento que de verdad los necesita.
Contexto. El delegado lee los archivos por su cuenta y devuelve un resultado. Los 200 KB que leyó nunca entran en tu conversación.
Radio de impacto. Los delegados son de solo lectura por defecto (read, grep, find, ls), aplicado en la
construcción de la sesión. Un modelo barato haciendo trabajo exploratorio no puede tocar tu árbol salvo que
lo habilites.
El delegado es siempre el agente pi. Codex, Grok, DeepSeek y el resto aportan el modelo detrás de él; esto no es un envoltorio de sus CLIs.
Related MCP server: cursor-agents-mcp
Un delegado solo es dirigible si dos canales permanecen abiertos: debes poder redirigirlo a mitad de tarea, y debe poder preguntarte algo y bloquearse hasta que respondas. La mayoría de las formas de conducir un agente de codificación desde otro programa cierran ambos.
| opencode SDK | este servidor | |
Se ejecuta en proceso | no (subproceso) | no (cliente HTTP a | sí ( |
Redirigir un turno en curso | no | solo |
|
El agente puede preguntarte algo | no ( | no en la API de sesión |
|
Modelo por llamada | no | sí | argumento |
pi -p y --mode json establecen ctx.hasUI = false. Un delegado iniciado así es de disparar y olvidar
por construcción: no puede plantear una pregunta y no puedes redirigirlo.
El SDK de opencode es un cliente tipado para un proceso de servidor separado: createOpencode() arranca
opencode serve y le habla por HTTP. Diseño limpio, pero implica un segundo proceso que supervisar,
y la superficie de sesión que expone (prompt, abort, revert, messages) no tiene
dirección a mitad de turno ni vía para que el agente pregunte nada a quien lo llama.
pi incluye createAgentSession como biblioteca embebible. Este servidor mantiene el objeto de sesión
en proceso, de modo que session.steer() puede colocar un mensaje después de la llamada de herramienta actual y antes de la
siguiente llamada al modelo, y un uiContext sintético captura las preguntas del agente y las aparca para
answer. No se lanza nada a un shell; no hay nada que supervisar.
* Las preguntas provienen de las extensiones de pi, por lo que ese canal está abierto solo para delegados creados con
extensions: true. Consulta Búsqueda web y otras herramientas de extensión.
(La tabla compara el canal de delegación, no el sandboxing; opencode tiene su propia configuración de permisos. Consulta Solo lectura por defecto para ver qué hace y qué no hace este servidor.)
Tool | Propósito |
| Llámalo primero. Informa de los modelos alcanzables, las herramientas permitidas y cómo dirigir un delegado. Cualquier otra herramienta se niega hasta que se ha ejecutado una vez. |
| Delega en segundo plano. Devuelve |
| Lanza hasta 10 delegados en una sola llamada. Se valida como lote, así que nada se inicia si una tarea es incorrecta. |
| Delega y bloquea hasta terminar. Solo para preguntas rápidas. |
| Estado, turnos, herramientas usadas, último texto y preguntas pendientes. |
| Redirige a un agente en ejecución. Se aplica después de su llamada de herramienta actual. |
| Da otro turno a un delegado ya terminado. Conserva todo lo que leyó, así no tienes que volver a explicar la tarea. |
| Responde a una pregunta mostrada por |
| Detiene una sesión; la salida parcial sigue siendo legible. |
| Lista los modelos que puede usar este delegado. |
| Lista sesiones, en ejecución y terminadas. Filtra por |
| Elimina una sesión terminada del historial, liberando su id. |
Requiere Node.js 22.19+ y una instalación funcional de pi en la que se haya iniciado sesión una vez
(pi, y luego /login).
claude mcp add pi -e PI_DELEGATE_MODEL=openrouter/stealth/ox-alpha -- npx -y pi-delegate-mcp.mcp.json{
"mcpServers": {
"pi": {
"command": "npx",
"args": ["-y", "pi-delegate-mcp"],
"env": { "PI_DELEGATE_MODEL": "openrouter/stealth/ox-alpha" },
"timeout": 1800000
}
}
}npx resuelve el paquete en cada lanzamiento. Para fijarlo, instálalo globalmente y llama al binario
directamente:
npm install -g pi-delegate-mcp{ "mcpServers": { "pi": { "command": "pi-delegate-mcp", "timeout": 1800000 } } }Mantén la clave del servidor corta, ya que prefija cada nombre de herramienta (mcp__pi__spawn).
git clone https://github.com/howznguyen/pi-delegate-mcp && cd pi-delegate-mcp
npm install && npm run build && npm linkPide a tu agente que delegue algo. Llama a init una vez para saber qué puede alcanzar este servidor,
y luego a spawn:
{ "id": "audit-01", "label": "who still imports onnxruntime",
"prompt": "Search this repo for anything still importing onnxruntime and list the files.",
"cwd": "/path/to/repo" }{ "sessionId": "audit-01", "state": "running", "model": "opencode-go/deepseek-v4-flash",
"activeTools": ["read", "grep", "find", "ls"] }spawn devuelve inmediatamente. Consulta con status el rastro ordenado de herramientas y la respuesta, o
sessions cuando haya varias en vuelo. Si init falla, dice exactamente qué falta: pi no
instalado, ningún proveedor con sesión iniciada o un ámbito de modelos que no coincide con nada.
Los nombres de modelo en los ejemplos siguientes son ilustrativos. Ejecuta models para ver qué puede alcanzar realmente
tu propia instalación de pi.
spawn y run aceptan tu propio id y una label de texto libre:
{
"id": "search-audit-01",
"label": "what ONNX removal left behind",
"prompt": "...",
"model": "opencode-go/deepseek-v4-flash"
}Los Ids son [A-Za-z0-9._:-], de 1 a 64 caracteres, deben empezar alfanuméricos y ser únicos entre las
sesiones activas. Omítelo para obtener un UUID.
Las sesiones terminadas siguen siendo legibles mediante status y sessions en lugar de desaparecer, para que puedas
volver y comprobar qué hizo realmente un delegado. Se conservan las PI_DELEGATE_HISTORY (50 por defecto) más recientes;
forget elimina una antes de tiempo.
status devuelve un rastro ordenado toolCalls: cada herramienta que ejecutó el delegado, con argumentos y
tiempos. Añade verbose: true para los ids de llamada y los resultados:
{
"seq": 1,
"id": "call_467b4bb4…",
"name": "bash",
"state": "ok",
"ms": 10,
"args": "{\"command\":\"echo hello-trace\"}",
"result": "hello-trace\n"
}Los argumentos y resultados se recortan (PI_DELEGATE_TRACE_ARGS, PI_DELEGATE_TRACE_RESULT) con la
longitud descartada registrada, de modo que un read de un archivo grande no puede inundar tu contexto.
Un delegado terminado no está agotado. pi conserva su sesión en memoria, así que follow_up vuelve a preguntar
al mismo agente con todo lo que ya leyó aún en contexto:
{ "sessionId": "search-audit-01", "prompt": "Now check whether the build files reference it too" }{ "sessionId": "search-audit-01", "state": "running", "turnsSoFar": 1 }El delegado continúa donde lo dejó. Todavía conserva los archivos que leyó en el primer turno, así que la segunda pregunta cuesta una llamada al modelo en lugar de una sesión nueva releyendo el repositorio.
Esta es la forma barata de mantener una conversación con un delegado. Crear uno nuevo significa re-explicar la tarea y pagar para que vuelva a leer los mismos archivos, y su respuesta llega sin nada del razonamiento que llevó hasta ella.
follow_up rechaza a un delegado que todavía está trabajando, porque redirigirlo a mitad de tarea es
para lo que sirve steer. Los dos no son intercambiables: steer aterriza entre llamadas de herramienta en un
agente en ejecución; follow_up inicia un nuevo turno en uno terminado.
spawn_batch inicia un lote completo en una llamada. Las tareas heredan el model, cwd,
tools y extensions a nivel de lote, y los sobrescriben individualmente donde lo necesiten:
{
"idPrefix": "audit",
"model": "opencode-go/deepseek-v4-flash",
"cwd": "/repo",
"tools": ["ls"],
"tasks": [
{ "prompt": "What still imports onnxruntime?", "label": "imports" },
{ "prompt": "Which build files still reference ONNX?", "label": "build" },
{
"prompt": "Any ONNX model files left on disk?",
"label": "artifacts",
"model": "opencode-go/ox-alpha-free"
}
]
}Eso las nombra audit-01, audit-02, audit-03 y devuelve en pocos milisegundos, ya que
lanzar un delegado no espera a que piense.
El lote se valida antes de que empiece nada: formato de id, ids duplicados dentro del lote, ids ya activos, herramientas bloqueadas y cada nombre de modelo. Una tarea incorrecta hace fallar la llamada y no lanza nada. Un abanico a medias es el peor resultado, porque pagas por los delegados que sí se iniciaron y aun así tienes que averiguar cuáles no lo hicieron.
Consulta todo el lote con una sola llamada a sessions en lugar de un status por delegado. Baja a
status solo para el delegado que realmente quieras leer. steer y abort siguen siendo por sesión.
model en cualquier llamada sobrescribe PI_DELEGATE_MODEL. Un nombre irresoluble es un error grave, nunca una
retirada silenciosa al modelo por defecto, porque una retirada silenciosa es como terminas facturando un modelo
que nunca pediste.
Qué nombres se resuelven lo decide el ámbito enabledModels propio de pi, que este servidor aplica
en lugar de limitarse a mostrar:
opencode-go/deepseek-v4-flash -> ok (listed in enabledModels)
opencode-go/glm-5.3 -> refused (out of scope)
knowns-hub/claude-opus -> ok (custom provider, see below)Los proveedores personalizados omiten el ámbito. Cualquier modelo servido por un proveedor declarado en
~/.pi/agent/models.json se ofrece incluso cuando enabledModels no lo nombra, con el argumento
de que declarar un proveedor a mano ya es una intención de usarlo. Por eso la lista puede ser
mucho más larga que enabledModels: tres entradas en el ámbito más dos proveedores personalizados pueden fácilmente
significar quince modelos ofrecidos. init lo dice explícitamente en models.scopeNote cuando aplica.
Dos interruptores cambian eso:
Efecto | |
| Respeta |
| Elimina el ámbito por completo. Todo modelo autenticado es usable. |
Llama a models para ver qué es realmente alcanzable según la configuración vigente.
Claude Code permite exactamente un comando statusLine, así que pi-delegate-statusline envuelve lo que
ya ejecutes y añade un segmento que muestra los delegados de este espacio de trabajo:
{
"statusLine": {
"type": "command",
"command": "PI_DELEGATE_STATUSLINE_WRAP=ccstatusline pi-delegate-statusline",
"refreshInterval": 10
}
}Elimina PI_DELEGATE_STATUSLINE_WRAP para imprimir solo el segmento de pi.
π ▸ audit engine·t1·12s audit index·t2·8s running, with turn counts and elapsed time
π ▸ migrate·t7·3m04s ?1 waiting one delegate is blocked on a question
π ✓2 finished, nothing runningFiltrar por directorio no basta: dos sesiones de Claude Code abiertas en el mismo repositorio mostrarían los delegados de la otra. La atribución usa en su lugar el linaje de procesos.
El host MCP crea un servidor por sesión, así que el servidor registra process.ppid, el pid del
host. La línea de estado, creada por ese mismo host, recorre su propia ascendencia y conserva solo los
archivos de estado cuyo hostPid encuentra ahí. Mismo repositorio, dos sesiones, sin interferencias. El
filtro de directorio sigue como respaldo para archivos de estado escritos antes de que esto existiera.
El estado vive en $XDG_STATE_HOME/pi-delegate-mcp/<pid>.json (PI_DELEGATE_STATE_DIR para
reubicarlo). Los archivos se podan cuando su proceso desaparece, solo con ESRCH, ya que EPERM significa que el
proceso está vivo bajo otro usuario. Los servidores también salen por sí solos cuando stdin se cierra o el
pid del host desaparece, así que un host que muere sin cerrar el transporte no deja nada atrás.
Las herramientas están bloqueadas a read, grep, find, ls en la construcción de la sesión. Cualquier otra cosa se rechaza
antes de que siquiera se cree una sesión.
Para ampliar eso, nombre las herramientas adicionales en el servidor:
"env": { "PI_DELEGATE_ALLOW_TOOLS": "bash" }o PI_DELEGATE_ALLOW_WRITE=1 para permitir todo.
bash no es un término medio. pi no incluye un sistema de permisos, así que un delegado que tenga bash
puede escribir archivos, borrarlos y alcanzar la red sin importar si write y edit están
en su lista. Rechazar esos dos mientras se permite bash registra su intención; no hace cumplir
nada. Los avisos de permisos y los hooks de Claude Code nunca ven lo que hace pi. Si necesita un límite
real, ejecute este servidor dentro de un contenedor.
Las herramientas propias de pi son read, grep, find, ls, bash, powershell, write, edit. No hay
búsqueda ni fetch entre ellas. Esas vienen de las extensiones de pi, que registran sus propias herramientas, y un
delegado puede usarlas.
Establezca extensions: true en la llamada y permita los nombres de las herramientas en el servidor:
"env": { "PI_DELEGATE_ALLOW_TOOLS": "web_search,fetch_content" }{ "prompt": "Find the current Node LTS version and tell me just the number",
"extensions": true, "tools": ["read", "grep", "find", "ls", "web_search"] }{ "seq": 1, "name": "web_search", "state": "ok", "ms": 2568,
"args": "{\"query\":\"latest stable Node.js LTS version\",\"numResults\":5}" }Así es como se le da a un delegado alcance de red sin entregarle bash. web_search puede buscar
y nada más, y pasa por la misma lista de permitidos que cualquier otra herramienta, así que el valor por defecto
de solo lectura no cambia para las llamadas que no lo piden.
Qué herramientas existen depende de lo que tenga instalado el usuario que ejecuta el servidor. pi-web-access proporciona
web_search, fetch_content, source_check y get_search_content. pi-mcp-adapter conecta los
servidores MCP en ~/.pi/agent/mcp.json y los expone como mcp. pi no tiene un cliente MCP propio, así que
esa extensión es la única ruta hacia uno.
extensions: true confía en todas las extensiones instaladas, no solo en la que quería. Se cargan como un
conjunto, se ejecutan con los privilegios completos del proceso de este servidor, y algunas abren sockets y temporizadores
que sobreviven a la sesión. Actívelo por llamada, para los delegados que lo necesiten, en lugar de dejarlo
activado por defecto. También cuesta tiempo de arranque real, por eso está desactivado a menos que se pida.
Variable de entorno | Por defecto | Significado |
| el propio de pi | Modelo usado cuando una llamada omite |
| sin definir | Lista separada por comas de herramientas adicionales a permitir, p. ej. |
| sin definir |
|
|
| Sesiones terminadas que se conservan para revisión |
|
| Máximo de caracteres de los argumentos de herramientas guardados en el rastro |
|
| Máximo de caracteres de los resultados de herramientas guardados en el rastro |
|
| Límite de tareas por llamada a |
|
| Por encima de esto, |
| directorio de estado XDG | Dónde se publica el estado de la línea de estado |
| sin definir | Comando de línea de estado para envolver y añadir |
| sin definir | Archivo al que añadir una marca de tiempo en cada render de la línea de estado, para depuración |
|
| Intervalo de notificación de progreso durante |
| sin definir |
|
| sin definir |
|
|
| Dónde se leen |
El SDK de MCP TypeScript tiene por defecto un tiempo de espera de solicitud de 60 segundos, que una tarea real superará. Tres defensas, en orden de preferencia:
Use spawn + status. Nada se bloquea, así que no aplica ningún tiempo de espera.
run emite notificaciones de progreso periódicas, que reinician el tiempo de espera del host.
Suba el límite con "timeout" en .mcp.json o MCP_TOOL_TIMEOUT en el entorno.
CLAUDE_AUTO_BACKGROUND_TASKS=1 hace que Claude Code ponga en segundo plano las llamadas MCP largas después de ~2 minutos.
Tenga en cuenta que las notificaciones de progreso se descartan una vez que una llamada se pone en segundo plano, así que elija (1) o (3),
no ambos.
El servidor no maneja credenciales. pi se autentica desde ~/.pi/agent/auth.json,
luego variables de entorno. Los hosts MCP a menudo lanzan servidores con un entorno reducido, así que
prefiera auth.json (ejecute pi una vez y /login) sobre exportar claves en un perfil de shell.
npm install
npm run build # tsc, src/*.ts -> dist/
npm run typecheck # tsc --noEmit, strict
npm run test:ci # offline: boots the server over stdio and lists its tools
npm test # full suite: needs a logged-in pi, makes real model callstest:ci es lo que ejecuta CI y lo que prepublishOnly exige, porque no necesita credenciales ni
red. npm test maneja delegados reales contra proveedores reales, así que cuesta dinero y solo
funciona donde pi ha iniciado sesión.
Ruta | Qué vive allí |
| Cada variable de entorno, leída en un solo lugar |
| La lista de permitidos de herramientas y la puerta que la hace cumplir |
| Mapa de sesiones, reclamación de ids, expulsión de historial |
| Un módulo por grupo de herramientas MCP |
| Todo lo que toca el SDK de pi |
| Publicación de archivos de estado y el binario de línea de estado |
Los lanzamientos están impulsados por etiquetas. npm version patch && git push --follow-tags ejecuta la compilación y las pruebas,
luego publica mediante publicación confiable OIDC, así que no se almacena ningún token npm en el repositorio.
Las incidencias y las solicitudes de extracción son bienvenidas. Si está informando de un delegado que se comportó mal, el
rastro toolCalls de status con verbose: true es lo útil para adjuntar.
abatilo/pi-mcp-bridge toma la ruta más simple:
genera pi --mode json -p --session-id <uuid> y deja que pi persista las sesiones en disco, así que el puente
no mantiene ningún estado. Elegante, y vale la pena leerlo. Cambia el control de dirección, preguntas y
control de herramientas para llegar allí.
MIT
Stop a running pi session. Partial output stays readable via status.
| Name | Required | Description | Default |
|---|---|---|---|
| sessionId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that partial output remains readable after abort, which is a useful behavioral detail beyond the simple action. It does not detail other side effects, but for a simple abort tool this is adequate.
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 clear sentence with an additional clause. It is front-loaded with the main action and adds a relevant detail. No wasted words, though it could be slightly more structured.
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 simplicity of the tool (one param, no output schema), the description covers the core action and a key consequence. However, it lacks details on error conditions, idempotency, or what 'running' means precisely. Acceptable but not comprehensive.
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 0%, and the description does not explain the sessionId parameter at all. The agent must infer that sessionId refers to the ID of the session to abort. With low coverage, the description should compensate, but it 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?
States the specific action 'Stop a running pi session' with a clear resource (pi session). It distinguishes from siblings like run, status, and spawn by focusing on termination. The verb 'abort' is reinforced by the description.
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?
Implies when to use (to stop a running session) but does not explicitly contrast with alternatives. However, it does mention that 'Partial output stays readable via status', which hints at using status afterwards. No explicit when-not to use, but the mention of status provides some context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Answer a question raised by a pi agent. Get requestId from status. Only pi extensions can ask, so questions appear only for delegates spawned with extensions: true; the MCP adapter's tool-approval and elicitation prompts are the usual source. A delegate waiting on one is blocked until you answer it.
| Name | Required | Description | Default |
|---|---|---|---|
| value | Yes | Chosen option, text, or boolean for a confirm | |
| requestId | Yes | ||
| sessionId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose a critical behavioral trait: 'A delegate waiting on one is blocked until you answer it,' i.e. this call has a real unblocking side effect. It also explains the origin of requests (MCP adapter tool-approval and elicitation prompts), which helps an agent recognize legitimate questions. It omits permission/auth requirements for the caller and what a successful answer returns.
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?
Three tight sentences, front-loaded with the core purpose and immediately followed by the operational detail (where to get requestId). No filler or restatement of the tool name. Slightly dense mid-sentence clause, but nothing wasted.
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 3-required-param, no-output-schema tool with no annotations, the description covers purpose, prerequisite lookup, source of requests, and the blocking consequence. The main remaining gap is that `sessionId` is never explained and there is no statement of what a valid answer looks like beyond the schema's `value` types.
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 only 33% (only `value` is described), so the description must compensate. It does add genuine meaning for `requestId` by pointing to `status` as its source. However, `sessionId` is left entirely unexplained in both schema and description, so the compensation is partial.
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 specific verb+resource ('Answer a question raised by a pi agent') that is clearly distinct from siblings like status, spawn, or steer. It scopes the tool to a narrow case (questions from pi extensions), so an agent can tell it apart from generic session tools. It stops just short of 5 because it never characterizes what an 'answer' does downstream beyond unblocking the caller.
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 gives a clear prerequisite chain: get `requestId` from `status`, and questions only exist for delegates spawned with `extensions: true`. That effectively tells the agent the condition under which this tool is callable. It doesn't state a when-not-to-use or name a fallback tool if no question is pending, so it falls short of explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send another prompt to a delegate that has already finished, keeping everything it read and said. Use this instead of spawning a fresh delegate and re-explaining the task: the session still holds its own context, which yours never had to absorb. Returns immediately; poll with status as usual. For a delegate that is still working, use steer instead.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The next turn for this delegate | |
| sessionId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given no annotations, the description carries the full burden. It discloses context preservation, immediate return (non-blocking), and the need to poll with `status`. It also states the pre‑condition (delegate finished). It doesn't cover error cases or side effects explicitly, but for this tool the key behaviors are well communicated.
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 pack purpose, usage, alternatives, and behavior with zero filler. The primary instruction (use for finished delegates) is front-loaded, and each clause serves a purpose.
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 2-parameter tool without an output schema, the description covers the essential workflow: when to use, what it does, and how to obtain results (poll via `status`). Minor gaps like error handling or repeated follow‑ups are not critical for an agent to call it 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?
The schema documents the `prompt` parameter, but `sessionId` is left undocumented. The description does not add explicit meaning for `sessionId` beyond the name and context. With 50% schema coverage, this is borderline; the description could have compensated by explaining that `sessionId` identifies the finished delegate session.
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?
Clear action (send another prompt) targeted at a specific resource (a finished delegate) while preserving context. Explicitly distinguishes from spawn and steer, making the tool's purpose unambiguous even among many siblings.
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?
Provides direct guidance to use this instead of spawning a fresh delegate, and explicitly directs to `steer` for a working delegate. The when-to-use and when-not-to-use conditions are spelled out, leaving no ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Drop a finished session from the review history, freeing its id for reuse.
| Name | Required | Description | Default |
|---|---|---|---|
| sessionId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It clearly discloses the destructive effect ('Drop'), the target ('review history'), and the side effect ('freeing its id for reuse'). It does not mention irreversibility or error behavior, but the core behavior is transparent and specific.
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, front-loaded sentence with no filler. Every word contributes meaning, and the most important action ('Drop') comes first.
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 one-parameter tool with no output schema, the description states the operation, the constraint (finished session), and the outcome (id reuse). It could have pointed to sessions for finding sessionId or to abort for running sessions, but nothing critical is missing for selecting and invoking the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema gives no description for sessionId, so the description adds meaning by tying it to a finished session's id and explaining the reuse consequence. It does not explicitly name the parameter or explain where to find sessionId, but the parameter name plus the description make the intent clear.
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 ('Drop') and resource ('finished session from the review history'), and clarifies the consequence ('freeing its id for reuse'). It also distinguishes itself from abort by specifying the session must be finished.
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 this is for finished sessions only, which separates it from running-session tools like abort. However, it never explicitly names an alternative or states when not to use this tool, leaving some routing inferred rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
READ THIS FIRST. Reports what this server can reach and how to drive it: permitted tools, the default model, models available per provider, and the recipes for delegating. Every other tool refuses until this has been called once.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Repository you intend to delegate in; picks up its project-local pi model scope | |
| models | No | Substring to filter the model list, e.g. "deepseek" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it discloses the most important behavior: all other tools refuse until init runs. It also makes clear this is a reporting/discovery call, implying read-only use, though it does not explicitly address repeated-call safety or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences front-load the critical directive and include the refusal behavior without any filler. Every sentence 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?
For a discovery tool with two optional parameters and no output schema, the description sufficiently lists what the agent will learn (reachable tools, default model, provider models, delegation recipes) and the prerequisite behavior, making it complete enough to call 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 coverage is 100%, so the baseline is 3. The description does not add meaning beyond the schema's existing explanations for cwd and models, though its mention of model listing aligns with the models parameter.
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 ('Reports') and names concrete resources: permitted tools, default model, provider models, and delegation recipes. It clearly positions init as the mandatory discovery/entry-point tool, distinguishing it from siblings like models, which only list models.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit ordering guidance: 'READ THIS FIRST' and 'Every other tool refuses until this has been called once.' This tells an agent exactly when to call init and that no sibling can substitute for it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List models this delegate may use: pi's own scoped set plus any custom provider. Use to pick a model value.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Picks up a project-local pi model scope | |
| filter | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the list scope (pi's scoped set plus custom providers) but does not mention side effects (none expected), output format, or ordering. For a read-only listing tool this is adequate but not rich; it does not contradict any structured data.
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 succinct sentences. The main purpose and usage are front-loaded, with no filler or redundant wording. 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?
For a simple listing tool with two parameters and no output schema, this description covers the core purpose and usage. However, the `filter` parameter is left undocumented, and the description does not mention the return format or any caveats, leaving some operational details unspecified.
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 50%: `cwd` has a description but `filter` does not. The tool description adds no meaning for `filter` or `cwd` beyond the schema, so the undocumented parameter remains unexplained. It fails to compensate for the schema gap.
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 'List models this delegate may use' with a specific verb and resource. It also specifies the scope ('pi's own scoped set plus any custom provider'), which distinguishes it from the sibling command-like tools (init, run, etc.) that perform actions rather than listings.
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 explicitly says 'Use to pick a `model` value', giving clear context for when to invoke it. It does not mention when not to use it or name alternatives, but given the sibling set are mostly action-oriented commands, the guidance is sufficient for selecting it correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delegate a task to a pi agent and wait for the final answer. Blocks until done. Prefer spawn for long work; this is for quick questions.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Your own session id for traceability, e.g. "search-audit-01". 1-64 chars of [A-Za-z0-9._:-], must start alphanumeric, must not already be in use. Defaults to a UUID. | |
| cwd | No | Working directory for the agent | |
| label | No | Free-text note shown in `sessions`, e.g. what this delegate is for | |
| model | No | Model as "provider/modelId", e.g. "openrouter/stealth/ox-alpha" | |
| tools | No | Tool allowlist for this delegate. [] disables all tools. Omit for defaults: read, grep, find, ls. Permitted on this server: read, grep, find, ls. | |
| prompt | Yes | The task for the pi agent | |
| extensions | No | Load pi extensions for this delegate. Off by default; they add startup cost and can misbehave. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it discloses the most consequential trait: the call blocks until the delegate finishes, and it returns the final answer. It does not cover failure/timeout behavior, cost, or isolation of the delegate, which leaves some gaps for an unattended blocking call.
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?
Three short sentences, zero waste, and the blocking constraint plus the routing guidance are front-loaded. Every sentence conveys a decision-relevant fact.
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 7-parameter delegation tool with full schema coverage and no output schema, the description supplies the missing return semantics ('final answer') and the blocking contract, which the schema cannot express. Minor gap: no mention of what happens on delegate failure or timeout.
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 all seven parameters (including id, tools allowlist, extensions, model) are already documented in the schema. The description adds no syntax or format meaning beyond that, so 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?
States a specific verb+resource ('Delegate a task to a pi agent') and clarifies the interaction model ('wait for the final answer'), then explicitly differentiates itself from the `spawn` sibling. An agent can distinguish this from spawn, spawn_batch, and follow_up without opening any schema.
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?
Names the alternative (`spawn`) and the exact condition that selects it ('long work') versus the condition for this tool ('quick questions'). This is an explicit when/when-not/alternative statement, which is the top of the scale.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List pi sessions held by this server, running and finished. Finished ones stay readable for review until evicted (keeps the newest 50).
| Name | Required | Description | Default |
|---|---|---|---|
| state | No | Filter by state: starting, running, done, aborted, error | |
| verbose | No | Include full text and tool calls |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose that finished sessions remain readable until evicted and keeps the newest 50, which is useful behavioral context. However, it does not mention any authentication requirements, rate limits, or the exact return format (e.g., whether it returns summaries or raw session objects). For a non-destructive list operation, this is partial transparency but not exhaustive.
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. The first states the core purpose, and the second adds a relevant retention policy. No fluff or redundancy; every word earns its place. It is front-loaded with the primary action and scope, making it easy for an agent to quickly grasp the tool's function.
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 low complexity (2 optional params, no output schema, no annotations), the description covers the essential aspects: what it lists, the state scope, and retention behavior. It does not explicitly describe the output format, but for a list tool this is often inferable. The lack of an output schema is partially offset by the clear description of the tool's behavior, making it adequately complete for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both 'state' and 'verbose' already documented. The description adds no new parameter-specific detail beyond what the schema provides—it references 'running and finished' which maps to a subset of state values, but this is already inferred from the schema's enum-like description. Since the schema carries the parameter semantics, the description's contribution is minimal, aligning with the baseline of 3.
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 begins with a specific verb and resource: 'List pi sessions held by this server, running and finished.' It clearly identifies the tool as a listing operation for sessions, and the mention of 'running and finished' distinguishes it from siblings like 'status' which likely targets a single session. The purpose is unambiguous.
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 listing sessions but does not explicitly contrast it with alternatives such as 'status' or 'forget'. No when-to-use/when-not-to-use guidance is provided, relying on the agent to infer when this tool is appropriate based on the action of listing. The retention note hints at review use cases, but no explicit routing to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Delegate a task to a pi agent running in the background. Returns a sessionId immediately, so nothing blocks. Poll with status, redirect with steer, answer its questions with answer. Use this for anything that might take more than a minute.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Your own session id for traceability, e.g. "search-audit-01". 1-64 chars of [A-Za-z0-9._:-], must start alphanumeric, must not already be in use. Defaults to a UUID. | |
| cwd | No | Working directory for the agent | |
| label | No | Free-text note shown in `sessions`, e.g. what this delegate is for | |
| model | No | Model as "provider/modelId", e.g. "openrouter/stealth/ox-alpha" | |
| tools | No | Tool allowlist for this delegate. [] disables all tools. Omit for defaults: read, grep, find, ls. Permitted on this server: read, grep, find, ls. | |
| prompt | Yes | The task for the pi agent | |
| extensions | No | Load pi extensions for this delegate. Off by default; they add startup cost and can misbehave. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description carries the burden and delivers the single most important trait: it returns a sessionId immediately and nothing blocks, so the agent knows not to expect an inline result. It omits other behavioral context such as permissions, session lifetime/cleanup (handled by `forget`/`abort`), and failure behavior.
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?
Three short sentences, front-loaded with the core action and followed by the async contract and lifecycle routing. No filler; every sentence carries actionable 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?
For a 7-parameter, no-output-schema tool this covers what an agent most needs: the async contract and the follow-up tools for polling, steering and answering. Residual gaps are minor – return payload shape beyond sessionId and failure/timeout behavior are unstated.
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 explains id, cwd, label, model, tools and extensions in detail. The description adds no parameter-level meaning beyond that (e.g. it never mentions the tools allowlist or model override), so the 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?
States a specific verb and resource: "Delegate a task to a pi agent running in the background," which is unambiguous. It implicitly separates itself from `run` via the timing heuristic ("more than a minute"), but never names `run` or `spawn_batch` explicitly, so sibling differentiation is inferred rather than stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives an explicit when-to-use rule ("anything that might take more than a minute") and then routes the agent through the full lifecycle: poll with `status`, redirect with `steer`, answer questions with `answer`. This is exactly the alternative-naming guidance an agent needs to pick and follow this tool correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fan out several delegates in one call. Each task inherits the batch-level model, cwd, tools and extensions unless it overrides them. The whole batch is validated before any delegate starts, so a bad model name or a duplicate id fails everything instead of leaving half a fan-out running. Poll the result with sessions, which reports all of them at once, rather than one status per delegate.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Default working directory for every task in this batch | |
| model | No | Default model for every task in this batch | |
| tasks | Yes | 1 to 10 delegates to start | |
| tools | No | Default tool allowlist for every task in this batch | |
| idPrefix | No | Names the tasks `<prefix>-01`, `<prefix>-02`, ... e.g. "audit" gives "audit-01" | |
| extensions | No | Default extensions setting for every task in this batch |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully covers behavioral traits: whole-batch validation before any start, failure semantics for bad model or duplicate id, and inheritance/override rules. It discloses key outcomes and edge-case behavior, though it does not mention async execution or session cleanup.
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 with no filler. The core purpose and key behavior are front-loaded; the polling guidance is a natural close. Every clause serves a purpose.
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 covers purpose, validation, inheritance, and polling—enough for correct invocation. Minor gaps like precise return format are covered by the `sessions` reference, so it is nearly complete for the complexity level.
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 6 parameters, so baseline is 3. The description adds meaningful semantics beyond the schema: it explains how batch-level defaults are overridden per task, clarifies the idPrefix format, and states the validation impact on parameters. This elevates it above the 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 clearly states the action: 'Fan out several delegates in one call.' It specifies the resource (delegates) and the batch nature, distinguishing it from the single-delegate spawn. The inheritance and validation details further clarify its exact role.
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 explicitly advises polling with `sessions` instead of per-delegate `status`, giving concrete guidance on expected follow-up. It implies batch use case but does not explicitly contrast with `spawn` for single-delegate scenarios, leaving some room for inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check a background pi session. Returns state, turn count, tools used, latest text, and any pending questions the agent is waiting on. A non-empty questions array means it is blocked until you call answer. toolCalls traces every tool the delegate ran, in order.
| Name | Required | Description | Default |
|---|---|---|---|
| verbose | No | Include tool results and call ids in the trace | |
| sessionId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the return contents (state, turn count, tools, latest text, pending questions) and explains the blocking semantics of the 'questions' array. It also notes that 'toolCalls' traces every tool run in order, adding behavioral depth beyond the tool name. It doesn't mention side effects, but 'check' implies read-only behavior, and the description sufficiently covers operational behavior.
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 concise and well-structured: two sentences plus a note. It front-loads the purpose, then details the return fields and the blocking condition. Every sentence carries useful information with no fluff.
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 absence of an output schema, the description adequately explains what the call returns and how to interpret the 'questions' array. It also clarifies the nature of 'toolCalls'. Minor omissions like error behavior for invalid sessions are not critical for a status-checking tool, so it feels complete enough for an agent to call it 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 coverage is only 50%: only 'verbose' has a description; 'sessionId' is undocumented. The tool description does not mention either parameter, failing to compensate for the uncovered 'sessionId'. It doesn't explain what constitutes a valid sessionId or how 'verbose' changes the output beyond the schema's minimal hint. With low coverage and no description support, this is a significant gap.
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 clear verb ('Check') and a specific resource ('background pi session'), and enumerates exactly what it returns (state, turn count, tools used, latest text, pending questions). This distinguishes it from siblings like 'sessions' (which likely lists sessions) and 'answer' (which handles questions). The purpose is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives actionable guidance on how to interpret the result: a non-empty 'questions' array means the agent is blocked and must call 'answer'. However, it does not explicitly state when to use this tool versus alternatives (e.g., 'sessions' for listing all sessions, or 'steer' for modifying a session). The when-to-use context is implied but not contrasted with siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Redirect a running pi agent mid-task. The message lands after its current tool call finishes, before the next model call. Use this instead of aborting when the agent is going the wrong way.
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes | ||
| sessionId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears the full burden of behavioral disclosure. It transparently explains the timing of when the message lands, which is a key behavioral trait. It does not mention error cases or lack of side effects, but for a simple steering action this is reasonably 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 two sentences, concise, and front-loaded with the core action and timing. Every word adds value without unnecessary detail.
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 tool with no annotations and no output schema, the description covers the primary use case and timing behavior. It lacks details on error handling or edge cases, but given the low complexity, it is fairly 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 coverage is 0% and the description does not explain the parameters at all. While 'sessionId' and 'message' are somewhat self-explanatory by name, the description fails to indicate which parameter identifies the agent or what the message content should be. The description should have compensated for the lack of schema documentation.
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 action ('redirect') on a specific resource ('running pi agent') and adds timing context (after current tool call, before next model call). It explicitly contrasts with the sibling 'abort', making the purpose unambiguous.
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 gives explicit guidance: use this instead of aborting when the agent is going the wrong way. This clearly tells the agent when to choose this tool over a direct alternative, leaving no ambiguity.
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.
v0.1.1answer2 fields changedInput schema / properties / value / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "boolean"
- }
-]Input schema / properties / value / typeAdded value: +[
+ "string",
+ "boolean"
+]run1 field changedInput schema / properties / tools / descriptionPrevious value: -"Tool allowlist for this delegate. Default: read, grep, find, ls. Permitted on this server: read, grep, find, ls."New value: +"Tool allowlist for this delegate. [] disables all tools. Omit for defaults: read, grep, find, ls. Permitted on this server: read, grep, find, ls."spawn1 field changedInput schema / properties / tools / descriptionPrevious value: -"Tool allowlist for this delegate. Default: read, grep, find, ls. Permitted on this server: read, grep, find, ls."New value: +"Tool allowlist for this delegate. [] disables all tools. Omit for defaults: read, grep, find, ls. Permitted on this server: read, grep, find, ls."v0.1.0abortanswerfollow_upforgetinitmodelsrunsessionsspawnspawn_batchstatussteerScored across 12 tools
Each tool targets a distinct state or action, and the three delegation entry points (spawn/run/spawn_batch) are explicitly differentiated by blocking behavior and fan-out. The message-sending trio (answer/steer/follow_up) is clearly disambiguated by delegate state, and descriptions even cross-reference each other (spawn vs steer vs follow_up).
Most names are concise lowercase verbs (spawn, run, steer, abort, forget, init) with a consistent compound pattern for spawn_batch/spawn variants. The deviation is noun-style list tools (sessions, models) and the short 'init', which break a strict verb convention but remain readable and predictable.
12 tools map cleanly onto the delegation lifecycle: launch (spawn/run/spawn_batch), monitor (status/sessions), interact (steer/follow_up/answer), stop (abort), and housekeeping (forget/models/init). Each earns its place with no redundant or filler tools.
The surface covers the full delegate lifecycle including batch fan-out, mid-task redirection, post-completion follow-up, Q&A unblocking, and cleanup. Minor gaps exist (e.g. no dedicated blocking wait-for-completion on a spawned session, no explicit per-provider model-filtering view), but agents can work around these via status/run.
Agent-native task management: your AI agent is the interface. Delegate to anyone by email.
Hand tasks, bugs and finished work to AI coding agents, and get back a write-up with evidence.
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
Build agents to automate any background task. Works with your ChatGPT/Claude subscription.
