Skip to main content
Glama

delimit_context_branch

Manage mutable working branches of a venture's context to explore alternative directions without affecting the main line.

Instructions

Manage mutable working branches of a venture's context (STR-048).

When to use: when exploring an alternative direction for a venture — a "what if we pivoted?" thread — and you want a write-isolated branch of the venture context rather than mutating the main line. Sub-actions: "list" inventories branches, "create" mints a new branch, "merge" folds a branch back into main. When NOT to use: for immutable point-in-time evidence (use delimit_context_snapshot — that creates a frozen capture; this is for mutable working areas), to read context data (use delimit_context_read), or for git branch operations on a code repo (use git directly).

Sibling contrast: delimit_context_snapshot is read-only history capture; this manages active, writeable branches. Compared to git branches, this operates on the venture context filesystem (ai.context_fs), not the code repo.

Side effects: depends on action. "list" is read-only. "create" writes a new branch namespace under the venture in ai.context_fs. "merge" mutates the venture's main namespace with the branch's contents, then closes the branch. None of these touch the code repository or any git state. No license gate, no notification, no ledger write.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ventureYesVenture namespace key. Required.
actionNoBranch sub-action, one of "list", "create", "merge". Default "list".list
branch_nameNoBranch name (required for create / merge).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

No annotations provided, but the description details side effects for each action: 'list' is read-only, 'create' writes new branch namespace, 'merge' mutates main namespace and closes branch. States no code repo, git state, license gate, notification, or ledger write.

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?

Well-structured with clear sections (when to use, not to use, sibling contrast, side effects). Every sentence adds value, no redundancy.

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?

Given tool complexity (multiple actions, 3 params, existing output schema), the description covers usage, side effects, and contrasts completely. No missing aspects.

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 behavioral context for actions but does not provide additional parameter details beyond 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 the tool manages mutable working branches of a venture's context, using specific verbs like 'manage' and resource description. It distinguishes from siblings like delimit_context_snapshot (read-only) and delimit_context_read.

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 provides 'When to use' (exploring alternative directions, write-isolated) and 'When NOT to use' (immutable evidence, reading context, git operations). Contrasts with delimit_context_snapshot and git directly.

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/delimit-ai/delimit-mcp-server'

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