How do I use pi-delegate-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@pi-delegate-mcp Delegate a repo-wide search for all usages of the deprecated API to pi." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

de en es ja ko ru zh

pi-delegate-mcp

by howznguyen

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

██████╗ ██╗    ██████╗ ███████╗██╗     ███████╗ ██████╗  █████╗ ████████╗███████╗
██╔══██╗██║    ██╔══██╗██╔════╝██║     ██╔════╝██╔════╝ ██╔══██╗╚══██╔══╝██╔════╝
██████╔╝██║    ██║  ██║█████╗  ██║     █████╗  ██║  ███╗███████║   ██║   █████╗
██╔═══╝ ██║    ██║  ██║██╔══╝  ██║     ██╔══╝  ██║   ██║██╔══██║   ██║   ██╔══╝
██║     ██║    ██████╔╝███████╗███████╗███████╗╚██████╔╝██║  ██║   ██║   ███████╗
╚═╝     ╚═╝    ╚═════╝ ╚══════╝╚══════╝╚══════╝ ╚═════╝ ╚═╝  ╚═╝   ╚═╝   ╚══════╝
                            ███╗   ███╗ ██████╗██████╗
                            ████╗ ████║██╔════╝██╔══██╗
                            ██╔████╔██║██║     ██████╔╝
                            ██║╚██╔╝██║██║     ██╔═══╝
                            ██║ ╚═╝ ██║╚██████╗██║
                            ╚═╝     ╚═╝ ╚═════╝╚═╝

npm node license

MCP server that exposes the pi coding agent as a delegable, steerable worker.

Point Claude Code (or any MCP host) at it and delegate work to any of pi's ~38 providers (DeepSeek, Grok, GLM, Kimi, Qwen, Codex, OpenRouter, local llama.cpp) with the sub-agent's context staying out of your main conversation.

What it's for

Your main harness runs on an expensive model, with a context window you care about. A lot of what it does doesn't need that model, and actively damages that context: grepping a repo for every call site, reading a 2000-line file to answer one question, auditing what a refactor left behind.

Hand that work to a delegate instead:

Cost. The grunt work runs on DeepSeek, GLM, Kimi, Qwen, or a local llama.cpp. You pay frontier prices only for the reasoning that actually needs them.
Context. The delegate reads the files on its own budget and returns a result. The 200 KB it read never enters your conversation.
Blast radius. Delegates are read-only by default (read, grep, find, ls), enforced at session construction. A cheap model doing exploratory work cannot touch your tree unless you opt it in.

The delegate is always the pi agent. Codex, Grok, DeepSeek and the rest supply the model behind it; this is not a wrapper around their CLIs.

Related MCP server: handoff-mcp

Why pi, and not opencode or a CLI wrapper?

A delegate is only steerable if two channels stay open: you must be able to redirect it mid-task, and it must be able to ask you something and block until you answer. Most ways of driving a coding agent from another program close both.

	`pi -p` / CLI wrappers	opencode SDK	this server
Runs in-process	no (subprocess)	no (HTTP client to `opencode serve`)	yes (`createAgentSession`)
Redirect a running turn	no	`abort` only	`steer`
Agent can ask you something	no (`ctx.hasUI` false)	not in the session API	`status` → `answer` *
Model per call	no	yes	`model` argument

pi -p and --mode json set ctx.hasUI = false. A delegate started that way is fire-and-forget by construction: it cannot raise a question, and you cannot redirect it.

opencode's SDK is a typed client for a separate server process: createOpencode() boots opencode serve and talks HTTP to it. Clean design, but it means a second process to supervise, and the session surface it exposes (prompt, abort, revert, messages) has no mid-turn steering and no path for the agent to ask the caller anything.

pi ships createAgentSession as an embeddable library. This server holds the session object in-process, so session.steer() can land a message after the current tool call and before the next model call, and a synthetic uiContext catches the agent's questions and parks them for answer. Nothing is shelled out; nothing has to be supervised.

* Questions come from pi extensions, so that channel is open only for delegates spawned with extensions: true. See Web search and other extension tools.

(The table compares the delegation channel, not sandboxing; opencode has its own permission config. See Read-only by default for what this server does and does not enforce.)

Tools

Tool	Purpose
`init`	Call first. Reports reachable models, permitted tools, and how to drive a delegate. Every other tool refuses until it has run once.
`spawn`	Delegate in the background. Returns `sessionId` immediately. Use this by default.
`spawn_batch`	Fan out up to 10 delegates in one call. Validated as a batch, so nothing starts if one task is bad.
`run`	Delegate and block until done. For quick questions only.
`status`	State, turns, tools used, latest text, and pending questions.
`steer`	Redirect a running agent. Lands after its current tool call.
`follow_up`	Give a finished delegate another turn. It keeps everything it read, so you do not re-explain the task.
`answer`	Answer a question surfaced by `status`. Only reachable with `extensions: true`, since only extensions can ask.
`abort`	Stop a session; partial output stays readable.
`models`	List models this delegate may use.
`sessions`	List sessions, running and finished. Filter by `state`, expand with `verbose`.
`forget`	Drop a finished session from history, freeing its id.

Install

Requires Node.js 22.19+ and a working pi install that has been logged in once (pi, then /login).

Claude Code

claude mcp add pi -e PI_DELEGATE_MODEL=openrouter/stealth/ox-alpha -- npx -y pi-delegate-mcp

Any MCP host, via `.mcp.json`

{
  "mcpServers": {
    "pi": {
      "command": "npx",
      "args": ["-y", "pi-delegate-mcp"],
      "env": { "PI_DELEGATE_MODEL": "openrouter/stealth/ox-alpha" },
      "timeout": 1800000
    }
  }
}

npx resolves the package on every launch. To pin it, install globally and call the binary directly:

npm install -g pi-delegate-mcp

{ "mcpServers": { "pi": { "command": "pi-delegate-mcp", "timeout": 1800000 } } }

Keep the server key short, since it prefixes every tool name (mcp__pi__spawn).

From source

git clone https://github.com/howznguyen/pi-delegate-mcp && cd pi-delegate-mcp
npm install && npm run build && npm link

First run

Ask your agent to delegate something. It calls init once to learn what this server can reach, then 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 returns immediately. Poll with status for the ordered tool trace and the answer, or sessions when several are in flight. If init fails, it says exactly what is missing: pi not installed, no provider logged in, or a model scope that matches nothing.

Model names in the examples below are illustrative. Run models to see what your own pi install can actually reach.

Traceability

spawn and run both accept your own id and a free-text label:

{
  "id": "search-audit-01",
  "label": "what ONNX removal left behind",
  "prompt": "...",
  "model": "opencode-go/deepseek-v4-flash"
}

Ids are [A-Za-z0-9._:-], 1-64 chars, must start alphanumeric, and must be unique among live sessions. Omit for a UUID.

Finished sessions stay readable via status and sessions instead of vanishing, so you can go back and check what a delegate actually did. The newest PI_DELEGATE_HISTORY (default 50) are kept; forget drops one early.

status returns an ordered toolCalls trace: every tool the delegate ran, with arguments and timing. Add verbose: true for call ids and results:

{
  "seq": 1,
  "id": "call_467b4bb4…",
  "name": "bash",
  "state": "ok",
  "ms": 10,
  "args": "{\"command\":\"echo hello-trace\"}",
  "result": "hello-trace\n"
}

Arguments and results are clipped (PI_DELEGATE_TRACE_ARGS, PI_DELEGATE_TRACE_RESULT) with the dropped length recorded, so one read of a large file cannot flood your context.

Giving a delegate another turn

A finished delegate is not spent. pi keeps its session in memory, so follow_up re-prompts the same agent with everything it already read still in context:

{ "sessionId": "search-audit-01", "prompt": "Now check whether the build files reference it too" }

{ "sessionId": "search-audit-01", "state": "running", "turnsSoFar": 1 }

The delegate picks up where it left off. It still holds the files it read on the first turn, so the second question costs one model call rather than a fresh session re-reading the repository.

This is the cheap way to have a conversation with a delegate. Spawning a fresh one means re-explaining the task and paying for it to re-read the same files, and its answer arrives with none of the reasoning that led there.

follow_up refuses a delegate that is still working, because redirecting one mid-task is what steer is for. The two are not interchangeable: steer lands between tool calls on a running agent, follow_up starts a new turn on a finished one.

Fanning out

spawn_batch starts a whole batch in one call. Tasks inherit the batch-level model, cwd, tools and extensions, and override them individually where they need to:

{
  "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"
    }
  ]
}

That names them audit-01, audit-02, audit-03 and returns in a few milliseconds, since launching a delegate does not wait for it to think.

The batch is validated before anything starts: id format, ids duplicated inside the batch, ids already live, blocked tools, and every model name. One bad task fails the call and launches nothing. Half a fan-out is the worst outcome, because you pay for the delegates that did start and still have to work out which ones did not.

Poll the whole batch with one sessions call rather than one status per delegate. Drop to status only for the delegate you actually want to read. steer and abort stay per session.

Picking a model per call

model on any call overrides PI_DELEGATE_MODEL. An unresolvable name is a hard error, never a silent fallback to the default model, because a silent fallback is how you end up billing a model you never asked for.

Which names resolve is decided by pi's own enabledModels scope, which this server enforces rather than merely displays:

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)

Custom providers bypass the scope. Any model served by a provider declared in ~/.pi/agent/models.json is offered even when enabledModels does not name it, on the grounds that declaring a provider by hand is already an intent to use it. This is why the list can be much longer than enabledModels: three entries in the scope plus two custom providers can easily mean fifteen offered models. init says so explicitly in models.scopeNote when it applies.

Two switches change that:

	Effect
`PI_DELEGATE_STRICT_SCOPE=1`	Honour `enabledModels` exactly. The custom-provider bypass is dropped.
`PI_DELEGATE_IGNORE_SCOPE=1`	Drop scoping altogether. Every authenticated model is usable.

Call models to see what is actually reachable under whichever setting is in force.

Status line

Claude Code allows exactly one statusLine command, so pi-delegate-statusline wraps whatever you already run and appends a segment showing this workspace's delegates:

{
  "statusLine": {
    "type": "command",
    "command": "PI_DELEGATE_STATUSLINE_WRAP=ccstatusline pi-delegate-statusline",
    "refreshInterval": 10
  }
}

Drop PI_DELEGATE_STATUSLINE_WRAP to print the pi segment alone.

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 running

Which delegates belong to which session

Filtering by directory is not enough: two Claude Code sessions open on the same repository would show each other's delegates. Attribution uses process lineage instead.

The MCP host spawns one server per session, so the server records process.ppid, the host's pid. The status line, spawned by that same host, walks its own ancestry and keeps only the state files whose hostPid it finds there. Same repo, two sessions, no crosstalk. The directory filter remains as a fallback for state files written before this existed.

State lives in $XDG_STATE_HOME/pi-delegate-mcp/<pid>.json (PI_DELEGATE_STATE_DIR to relocate). Files are pruned when their process is gone, ESRCH only, since EPERM means the process is alive under another user. Servers also exit on their own when stdin closes or the host pid disappears, so a host that dies without closing the transport leaves nothing behind.

Read-only by default

Tools are locked to read, grep, find, ls at session construction. Anything else is refused before a session is even created.

To widen that, name the extra tools on the server:

"env": { "PI_DELEGATE_ALLOW_TOOLS": "bash" }

or PI_DELEGATE_ALLOW_WRITE=1 to permit everything.

bash is not a middle ground. pi ships no permission system, so a delegate holding bash can write files, delete them, and reach the network regardless of whether write and edit are on its list. Refusing those two while allowing bash records your intent; it does not enforce anything. Claude Code's permission prompts and hooks never see what pi does. If you need a real boundary, run this server inside a container.

Web search and other extension tools

pi's own tools are read, grep, find, ls, bash, powershell, write, edit. There is no search and no fetch among them. Those come from pi extensions, which register their own tools, and a delegate can use them.

Set extensions: true on the call and permit the tool names on the server:

"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}" }

This is how you give a delegate network reach without handing it bash. web_search can search and nothing else, and it passes through the same allowlist as every other tool, so the read-only default is unchanged for calls that do not ask for it.

Which tools exist depends on what the user running the server has installed. pi-web-access provides web_search, fetch_content, source_check and get_search_content. pi-mcp-adapter bridges the MCP servers in ~/.pi/agent/mcp.json and exposes them as mcp. pi has no MCP client of its own, so that extension is the only route to one.

extensions: true trusts every installed extension, not just the one you wanted. They load as a set, they run with the full privileges of this server's process, and some open sockets and timers that outlive the session. Turn it on per call, for the delegates that need it, rather than leaving it on by default. It also costs real startup time, which is why it is off unless asked for.

Configuration

Env var	Default	Meaning
`PI_DELEGATE_MODEL`	pi's own default	Model used when a call omits `model`
`PI_DELEGATE_ALLOW_TOOLS`	unset	Comma list of extra tools to permit, e.g. `bash`
`PI_DELEGATE_ALLOW_WRITE`	unset	`1` permits every tool
`PI_DELEGATE_HISTORY`	`50`	Finished sessions kept for review
`PI_DELEGATE_TRACE_ARGS`	`400`	Max chars of tool arguments kept in the trace
`PI_DELEGATE_TRACE_RESULT`	`600`	Max chars of tool results kept in the trace
`PI_DELEGATE_BATCH_MAX`	`10`	Ceiling on tasks per `spawn_batch` call
`PI_DELEGATE_LIST_CAP`	`60`	Above this, `init` summarises models by provider instead of listing them
`PI_DELEGATE_STATE_DIR`	XDG state dir	Where status-line state is published
`PI_DELEGATE_STATUSLINE_WRAP`	unset	Status line command to wrap and append to
`PI_DELEGATE_STATUSLINE_LOG`	unset	File to append a timestamp to on every status line render, for debugging
`PI_DELEGATE_PROGRESS_MS`	`15000`	Progress notification interval during `run`
`PI_DELEGATE_IGNORE_SCOPE`	unset	`1` ignores pi's `enabledModels` scope, allowing any configured model
`PI_DELEGATE_STRICT_SCOPE`	unset	`1` honours `enabledModels` exactly, dropping the custom-provider bypass
`PI_CODING_AGENT_DIR`	`~/.pi/agent`	Where pi's `auth.json` and config are read from

Long-running work

The MCP TypeScript SDK defaults to a 60 second request timeout, which a real task will blow through. Three defences, in order of preference:

Use spawn + status. Nothing blocks, so no timeout applies.
run emits periodic progress notifications, which reset the host's timeout.
Raise the ceiling with "timeout" in .mcp.json or MCP_TOOL_TIMEOUT in the environment.

CLAUDE_AUTO_BACKGROUND_TASKS=1 makes Claude Code background long MCP calls after ~2 minutes. Note that progress notifications are discarded once a call is backgrounded, so pick (1) or (3), not both.

Auth

The server does not handle credentials. pi authenticates itself from ~/.pi/agent/auth.json, then environment variables. MCP hosts often launch servers with a stripped environment, so prefer auth.json (run pi once and /login) over exporting keys in a shell profile.

Development

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 calls

test:ci is what CI runs and what prepublishOnly gates on, because it needs no credentials and no network. npm test drives real delegates against real providers, so it costs money and only works where pi has been logged in.

Path	What lives there
`src/config.ts`	Every environment variable, read in one place
`src/permissions.ts`	The tool allowlist and the gate that enforces it
`src/registry.ts`	Session map, id claiming, history eviction
`src/tools/`	One module per group of MCP tools
`src/pi/`	Everything that touches the pi SDK
`src/statusline/`	State file publishing and the status line binary

Releases are tag-driven. npm version patch && git push --follow-tags runs the build and tests, then publishes over OIDC trusted publishing, so no npm token is stored anywhere in the repository.

Issues and pull requests are welcome. If you are reporting a delegate that misbehaved, the toolCalls trace from status with verbose: true is the useful thing to attach.

Prior art

abatilo/pi-mcp-bridge takes the simpler route: spawn pi --mode json -p --session-id <uuid> and let pi persist sessions on disk, so the bridge holds no state at all. Elegant, and worth reading. It trades away steering, questions, and tool control to get there.

License

MIT

Available Tools

12 tools

abortA

Stop a running pi session. Partial output stays readable via status.

ParametersJSON Schema

Name	Required	Description	Default
`sessionId`	Yes

TDQS

A3.5/5.0

Behavior4/5

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.

Conciseness4/5

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.

Completeness3/5

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.

Parameters1/5

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.

Purpose5/5

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.

Usage Guidelines3/5

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.

answerA

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.

ParametersJSON Schema

Name	Required	Description
`value`	Yes	Chosen option, text, or boolean for a confirm
`requestId`	Yes
`sessionId`	Yes

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses that answering unblocks the delegate, that questions only originate from pi extensions, and points to obtaining requestId from status. It does not mention potential side effects, permissions needed, or what happens if the value is invalid, but the key blocking behavior is disclosed. It adds useful context beyond the raw schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences, front-loaded with the core purpose, then critical usage conditions and unblocking note. No wasted words, all content earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with no output schema, the description covers the essential operational context: how to get requestId, when questions arise, and that answering resolves a block. It doesn't spec edge cases, but the minimum needed for correct invocation is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, so description must compensate. It explains requestId (retrieve from status), but sessionId is not described. Value is already described in the schema as string/boolean with a confirm purpose, so that's covered. The description adds meaningful guidance for requestId, but sessionId remains undocumented. Partial compensation, not full.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool answers a question raised by a pi agent, identifies the resource (question) and the action (answer). It differentiates from siblings by specifying the context (pi extensions, delegates with extensions:true) and that it's distinct from other tools like run, steer, or follow_up. The specificity of 'question raised by a pi agent' removes ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly describes when to use: only for questions from pi extensions, which appear only for delegates spawned with extensions:true, and specifically notes the MCP adapter's tool-approval and elicitation prompts as typical sources. Also states that a waiting delegate is blocked until answered, implying urgency. This gives clear conditions and even hints at the source of requests.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

follow_upA

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.

ParametersJSON Schema

Name	Required	Description	Default
`prompt`	Yes	The next turn for this delegate
`sessionId`	Yes

TDQS

A4.4/5.0

Behavior4/5

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.

Conciseness5/5

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.

Completeness4/5

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.

Parameters3/5

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.

Purpose5/5

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.

Usage Guidelines5/5

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.

forgetA

Drop a finished session from the review history, freeing its id for reuse.

ParametersJSON Schema

Name	Required	Description	Default
`sessionId`	Yes

TDQS

A4.2/5.0

Behavior4/5

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.

Conciseness5/5

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.

Completeness4/5

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.

Parameters4/5

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.

Purpose5/5

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.

Usage Guidelines3/5

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.

initA

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.

ParametersJSON Schema

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"

TDQS

A4.5/5.0

Behavior4/5

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.

Conciseness5/5

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.

Completeness5/5

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.

Parameters3/5

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.

Purpose5/5

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.

Usage Guidelines5/5

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.

modelsA

List models this delegate may use: pi's own scoped set plus any custom provider. Use to pick a model value.

ParametersJSON Schema

Name	Required	Description	Default
`cwd`	No	Picks up a project-local pi model scope
`filter`	No

TDQS

A3.8/5.0

Behavior3/5

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.

Conciseness5/5

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.

Completeness3/5

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.

Parameters2/5

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.

Purpose5/5

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.

Usage Guidelines4/5

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.

runA

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.

ParametersJSON Schema

Name	Required	Description
`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. Default: 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.

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It does disclose key behavior: 'Blocks until done' and waits for the final answer. However, it omits failure modes, timeout behavior, cancellation, and side effects, which matter for a synchronous delegation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short clauses, each earning its place: what the tool does, that it blocks, and when to choose the sibling instead. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a synchronous task-delegation tool, the description covers purpose, blocking behavior, and the key alternative. It lacks explicit return-format details and any mention of error behavior, but the schema covers all parameters and no output schema exists, so the remaining gap is modest.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all seven parameters already have individual descriptions. The prose adds no parameter-specific detail beyond characterizing the prompt as a quick task, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

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 and wait for the final answer.' It also explicitly contrasts with spawn, distinguishing this synchronous 'quick question' tool from the long-running sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to prefer `spawn` for long work and frames `run` as for quick questions. This gives the agent a clear decision rule for choosing between siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

sessionsA

List pi sessions held by this server, running and finished. Finished ones stay readable for review until evicted (keeps the newest 50).

ParametersJSON Schema

Name	Required	Description	Default
`state`	No	Filter by state: starting, running, done, aborted, error
`verbose`	No	Include full text and tool calls

TDQS

A3.8/5.0

Behavior3/5

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.

Conciseness5/5

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.

Completeness4/5

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.

Parameters3/5

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.

Purpose5/5

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.

Usage Guidelines3/5

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.

spawnA

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.

ParametersJSON Schema

Name	Required	Description
`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. Default: 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.

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden. It correctly discloses the most critical behavior — non-blocking, immediate return, and background execution. But it adds nothing about failure modes, session persistence, resource usage, or concurrency limits, which are meaningful for an async delegation tool. The core async trait is covered; the periphery is not.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, zero filler. Purpose is front-loaded, the non-blocking behavior follows, the companion tools are listed, and the usage threshold closes. Every sentence earns its place with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an async 7-param tool with no output schema and no annotations, the description conveys the essential flow (spawn → poll/steer/answer) and the non-blocking nature. But it leaves lifecycle gaps unaddressed — error/timeout behavior, whether sessions persist across restarts, and cost/billing implications. Adequate for core invocation, incomplete for edge behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds no parameter-level meaning beyond the schema — it neither enriches `prompt`, `id`, nor `tools`, which would justify a higher score. It neither conflicts with nor supplements the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Delegate'), a resource ('a pi agent running in the background'), and the defining behavior (returns a sessionId immediately, non-blocking). This strongly differentiates it from the synchronous sibling `run` and the batch-oriented `spawn_batch`. The async nature is made explicit and front-loaded.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides an explicit usage threshold ('anything that might take more than a minute') and names the companion tools (`status`, `steer`, `answer`) for the subsequent lifecycle. However, it never explicitly names the alternative for short tasks (`run`) or states a when-not condition, leaving that distinction implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

spawn_batchA

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.

ParametersJSON Schema

Name	Required	Description
`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

TDQS

A4.4/5.0

Behavior4/5

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.

Conciseness5/5

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.

Completeness4/5

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.

Parameters4/5

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.

Purpose5/5

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.

Usage Guidelines4/5

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.

statusA

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.

ParametersJSON Schema

Name	Required	Description	Default
`verbose`	No	Include tool results and call ids in the trace
`sessionId`	Yes

TDQS

A3.9/5.0

Behavior4/5

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.

Conciseness5/5

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.

Completeness4/5

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.

Parameters2/5

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.

Purpose5/5

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.

Usage Guidelines3/5

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.

steerA

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.

ParametersJSON Schema

Name	Required	Description	Default
`message`	Yes
`sessionId`	Yes

TDQS

A4.3/5.0

Behavior4/5

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.

Conciseness5/5

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.

Completeness4/5

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.

Parameters2/5

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.

Purpose5/5

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.

Usage Guidelines5/5

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.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

12 tool updatesv0.1.0Aug 26, 2026
- First observedabort
- First observedanswer
- First observedfollow_up
- First observedforget
- First observedinit
- First observedmodels
- First observedrun
- First observedsessions
- First observedspawn
- First observedspawn_batch
- First observedstatus
- First observedsteer

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored 2026-08-26 02:16 across 12 tools

Disambiguation5/5

Each tool targets a distinct phase of the delegate lifecycle: starting (spawn, run, spawn_batch), monitoring (status, sessions), interacting (steer, answer, follow_up), and cleanup (abort, forget). Descriptions clearly differentiate async vs sync and running vs finished states, so misselection is unlikely.

Naming Consistency4/5

Most tools use imperative single-word verbs (spawn, steer, abort) or compound verbs (spawn_batch, follow_up), but two are bare nouns (sessions, models) instead of list-style verbs like list_sessions. This is a minor deviation from an otherwise predictable, straightforward naming scheme.

Tool Count5/5

At 12 tools, the server is well-scoped for its purpose—managing delegated pi agents. Each tool covers a necessary operation without redundancy, and the count falls comfortably within the 3–15 ideal range for a focused MCP server.

Completeness5/5

The tool surface provides full lifecycle coverage: launch, monitor, interact, redirect, follow-up, abort, clean up, and list. It also includes init and models for setup and model selection. There are no obvious gaps that would cause agent dead-ends.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

AgentdaOAuth
com.myagentda
Agent-native task management: your AI agent is the interface. Delegate to anyone by email.
Project Management Agent Orchestration Communication
2
tell.dev
dev.tell
Your coding agent tells a coworker's agent what you found or changed. Invite-only.
Agent Orchestration Coding Agents Developer Tools
1
ParleyOAuth
dev.weldra
Coordination hub for AI coding agents: message teammates, ask humans, audit every event.
Autonomous Agents Developer Tools
1
NoClick AOAuth
io.github.noclickapp
Build agents to automate any background task. Works with your ChatGPT/Claude subscription.
App Automation Autonomous Agents
4711

Related MCP Servers

pi-subagent
Coding Agents Command Line
guyiicn
A
license
C
quality
B
maintenance
Enables MCP hosts to delegate coding tasks to Pi CLI as a programmable sub-agent with session tracking and process management.
Updated a month ago (2026-08-18 22:04 UTC)
7
3
MIT
handoff-mcp
felkru
A
license
A
quality
C
maintenance
Enables Claude to delegate tasks to external coding agents (Codex or Antigravity) for independent reviews, separate quota usage, and async processing.
Updated 2 months ago (2026-07-21 18:35 UTC)
6
MIT
Leetcoder
Coding Agents Autonomous Agents Developer Tools
CommanderTurtle
A
license
Not graded
quality
B
maintenance
Enables Hermes agents to delegate bounded coding tasks to persistent oh-my-pi sessions with isolated git worktrees, live steering, and durable follow-ups, requiring explicit user confirmation before each task.
Updated 22 days ago (2026-08-26 11:55 UTC)
AGPL 3.0
omp-worker-mcp
Autonomous Agents Agent Orchestration Developer Tools
divenire990
A
license
A
quality
A
maintenance
Enables delegating asynchronous coding tasks and DAG workflows to local Oh My Pi (OMP) CLI sub-agents, with topological orchestration, path isolation, and supervised resumption.
Updated 19 days ago (2026-08-29 06:55 UTC)
9
35 npm
1
MIT

What it's for

Why pi, and not opencode or a CLI wrapper?

Tools

Install

Claude Code

Any MCP host, via .mcp.json

From source

First run

Traceability

Giving a delegate another turn

Fanning out

Picking a model per call

Status line

Which delegates belong to which session

Read-only by default

Web search and other extension tools

Configuration

Long-running work

Auth

Development

Prior art

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Any MCP host, via `.mcp.json`