Skip to main content
Glama

Delegate work to a Capy agent

capy_delegate

Start a cloud agent to complete engineering work independently, then monitor progress with status or block until done.

Instructions

Start a new Capy agent thread in the cloud to do a piece of engineering work. The agent runs in its own isolated VM with the project's repos checked out, and works independently of this conversation. Call this once per independent piece of work: calling it several times gives you several agents running genuinely in parallel.

Write the prompt the way you would brief a competent engineer who cannot ask you follow-up questions: state the goal, the acceptance criteria, and any constraint that is not obvious from the code.

Returns a thread id. Use capy_wait to block until the work is done, or capy_status to poll. Note that starting a thread consumes Capy credits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoLowercase tags to attach, useful for grouping a batch of parallel delegations so you can find them later with capy_list (e.g. ["refactor-batch"]).
modelNoModel for the Captain (planner) agent. Omit to use the project default. List available models with capy_models.
reposNoOverride which repos and branches the agent starts from.
speedNoCaptain speed setting.
promptYesWhat the agent should do. Be specific about goal and acceptance criteria.
reasoningNoCaptain reasoning effort.
project_idNoCapy project id. Defaults to CAPY_PROJECT_ID. List them with capy_projects.
build_modelNoModel for the build (executor) agent, if it should differ from the Captain.
build_speedNoBuild agent speed setting.
slack_channelNoMirror the thread into this Slack channel, if Slack is connected.
build_reasoningNoBuild agent reasoning effort.
Behavior4/5

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

Annotations already provide readOnlyHint=false, openWorldHint=true, etc. Description adds valuable context: consumes credits, runs independently, isolated VM. No contradictions. Together, they give a clear behavioral picture.

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?

Well-structured with key information front-loaded. A couple of sentences could be trimmed, but overall efficient and organized. Earns its length.

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?

Covers main points: purpose, parallelism, follow-up tools, cost, prompt advice. No output schema, but mentions return of thread id. Adequate for a delegation tool with many optional parameters.

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 baseline 3. Description adds some value by emphasizing prompt quality and noting default model behavior, but doesn't significantly expand on schema descriptions.

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 it starts a new Capy agent thread to perform engineering work in an isolated VM. It distinguishes from siblings by mentioning capy_wait and capy_status for follow-up, and explains that multiple calls yield genuine parallelism.

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 explicit guidance: 'Call this once per independent piece of work' and indicates alternative tools (capy_wait, capy_status) for monitoring. Also covers cost and prompt crafting advice. Could be stronger on when-not-to-use, but sufficient.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Takumixbt/capy-fleet'

If you have feedback or need assistance with the MCP directory API, please join our Discord server