hive

Overview Schema Source Related Servers Discussions Admin

agent_park

Park an unfinished worker for the night: stop the session, mark it as PARKED rather than closed, record the branch, and get the resume call to bring it back.

Instructions

Park a claude or codex worker for the night: kill its pane, mark the row PARKED rather than plain closed, record the branch, and hand back a board line plus the one call that brings it back. Use this instead of agent_close when the lane is paused, not finished - closed alone cannot tell a next-morning lead which is which. Resume it with agent_resume.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	The worker's name, e.g. "impl" or "DEVX-123". Prefer passing this rather than agent_id, but pass only one: if both arrive, agent_id wins and this is ignored. A partial name works when it matches exactly one running worker, so "123" finds DEVX-123.
`agent_id`	No	Numeric agent id. Use name instead unless you have the id to hand.
`project_id`	No	Different project override. Use ONLY when the user explicitly asks for another project by name; otherwise stay in the current scope, even when results are empty.
`confirm_self`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`cwd`	Yes
`name`	Yes
`note`	No
`parked`	Yes
`agent_id`	Yes
`todo_ids`	Yes
`parked_at`	Yes
`board_line`	Yes
`session_id`	Yes
`parked_branch`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Sep 22, 2026

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 transparency burden. It discloses the destructive action ('kill its pane'), the state distinction ('PARKED rather than plain closed'), a side effect ('record the branch'), and the return content ('board line plus the one call that brings it back'). This goes well beyond a generic 'parks a worker' statement, though it could mention preconditions like privileges or failure 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?

Three sentences with zero waste: the first delivers the action, the second the decision rule versus agent_close, and the third names the resume counterpart. The key scoping distinction is front-loaded.

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?

The tool has meaningful side effects and a distinctive return ('board line plus the one call that brings it back'), all covered. The output schema exists so return details need not be repeated. The only gap is confirm_self semantics, which even the schema leaves blank, but this is minor given the overall guidance.

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 75% and the schema already provides rich guidance for name, agent_id, and project_id. The description adds no parameter-specific details and leaves confirm_self undocumented, but the schema handles most of the burden, so a 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?

The description states a specific verb and resource with concrete outcomes: 'Park a claude or codex worker... kill its pane, mark the row PARKED rather than plain closed, record the branch, and hand back a board line plus the one call that brings it back.' It clearly differentiates from agent_close by the paused-vs-finished criterion.

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 gives the when-to-use rule: 'Use this instead of agent_close when the lane is paused, not finished,' and names the complementary tool: 'Resume it with agent_resume.' No ambiguity about when to pick this tool.

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