Skip to main content
Glama

Delimit Context Impl

_delimit_context_impl
DestructiveIdempotent

Manage a versioned, venture-scoped context filesystem so plans and artifacts persist across sessions and models. Offers list, read, write, snapshot, branch, and init actions.

Instructions

Unified context-filesystem entry point — dispatches to one of six actions.

Manages a venture-scoped, versioned context filesystem under ~/.delimit/context// so plans, decisions, and artifacts survive across sessions and across models. This is the cross-model- continuity store: write once, read from any later session or any other assistant.

When to use: as the single MCP-registered context surface (delimit_context) when the caller wants to pick the action by name in one call rather than choosing a specific delimit_context_* alias. When NOT to use: from internal code paths — prefer the specific alias (delimit_context_read, delimit_context_write, delimit_context_snapshot, etc.) so each action's docstring, args, and side-effect notes show up at the right call site. For ephemeral, conversation-scoped memory use delimit_memory_store / delimit_memory_search instead — those are NOT venture-namespaced or versioned.

Sibling contrast: each delimit_context_ wrapper below is a thin alias over this implementation; they exist so the action's docstring lives at the right name. This is the dispatch core. The context FS is venture-scoped and versioned (snapshot/branch); delimit_memory_* is conversation-scoped and unversioned. Snapshot vs branch: snapshot is an immutable point-in-time copy (history/ rollback), branch is a mutable write-isolated fork that can be merged back into main. Neither touches git or any code repository.

Side effects: all six actions are free-tier (no require_premium gate in this dispatcher). Each routes to a distinct context-FS backend function and is wrapped via _with_next_steps for orchestrator hints. Per action:

  • "list" — read-only enumeration of /artifacts/*. Returns [] (no error) if the venture or artifacts dir does not exist.

  • "read" — read-only load of one artifact. Returns {"error": ...} if the named artifact is absent.

  • "init" — WRITES. Creates the venture directory, the memory/plans/artifacts/snapshots/branches subdirs, and manifest.json if absent. Idempotent.

  • "write" — WRITES/overwrites /artifacts/.json and bumps the manifest version counter. Overwrites silently if the artifact name already exists.

  • "snapshot" — WRITES. Copies the venture's artifacts/ and memory/ into a timestamped (optionally labeled) snapshot dir plus a snapshot manifest. Does NOT bump the version counter.

  • "branch" — depends on branch_action. "list" is read-only. "create" WRITES a new branch fork (copy of artifacts/ + memory/) and errors if the branch already exists. "merge" MUTATES the venture's main artifacts/ and memory/ with the branch's files, then DELETES the branch dir and bumps the version counter; errors if the branch is not found. Errors are deterministic ({"error": "..."}): an unknown top-level action, an unknown branch_action, or a missing branch_name on create/merge all short-circuit before the backend call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoArtifact name, used as the <name>.json file key. Required for action="read" and action="write". Ignored by other actions.
labelNoOptional human-readable snapshot label, appended to the timestamp in the snapshot dir name. Used only when action="snapshot".
actionNoWhich context operation to perform. One of "init", "read", "write", "list", "snapshot", "branch". Default "list". Other values return a deterministic error.list
contentNoArtifact text body. Used only when action="write".
ventureNoVenture/project namespace key — selects the ~/.delimit/context/<venture>/ tree. Used by every action. Default "default".default
branch_nameNoBranch name. Required when action="branch" with branch_action="create" or "merge"; ignored for "list".
artifact_typeNoType hint stored on the artifact — "text", "json", "code", or "plan". Used only when action="write". Default "text". Affects the stored type hint, not the storage format.text
branch_actionNoBranch sub-action — "list", "create", or "merge". Used only when action="branch". Default "list".list

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed8 schema fields changedv4.13.1
    • changedInput schema / properties / action / description
      Previous value: -"Which context operation to perform."New value: +"Which context operation to perform. One of \"init\", \"read\",\n\"write\", \"list\", \"snapshot\", \"branch\". Default \"list\". Other\nvalues return a deterministic error."
    • changedInput schema / properties / artifact_type / description
      Previous value: -"Type hint text/json/code/plan (for action='write')."New value: +"Type hint stored on the artifact — \"text\", \"json\",\n\"code\", or \"plan\". Used only when action=\"write\". Default\n\"text\". Affects the stored type hint, not the storage format."
    • changedInput schema / properties / branch_action / description
      Previous value: -"Branch sub-action create/merge/list (for action='branch')."New value: +"Branch sub-action — \"list\", \"create\", or \"merge\".\nUsed only when action=\"branch\". Default \"list\"."
    • changedInput schema / properties / branch_name / description
      Previous value: -"Branch name (for action='branch' with create/merge)."New value: +"Branch name. Required when action=\"branch\" with\nbranch_action=\"create\" or \"merge\"; ignored for \"list\"."
    • changedInput schema / properties / content / description
      Previous value: -"Artifact content (for action='write')."New value: +"Artifact text body. Used only when action=\"write\"."
    • changedInput schema / properties / label / description
      Previous value: -"Snapshot label (for action='snapshot')."New value: +"Optional human-readable snapshot label, appended to the\ntimestamp in the snapshot dir name. Used only when\naction=\"snapshot\"."
    • changedInput schema / properties / name / description
      Previous value: -"Artifact name (for read/write)."New value: +"Artifact name, used as the <name>.json file key. Required\nfor action=\"read\" and action=\"write\". Ignored by other\nactions."
    • changedInput schema / properties / venture / description
      Previous value: -"Venture/project namespace (default: \"default\")."New value: +"Venture/project namespace key — selects the\n~/.delimit/context/<venture>/ tree. Used by every action.\nDefault \"default\"."
  2. Addedv4.5.5

TDQS

A4.1/5.0
Behavior1/5

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

The description itself is highly transparent, enumerating per-action side effects, deterministic errors, and which actions write vs read. However, it directly contradicts the idempotentHint:true annotation: write bumps a version counter, snapshot creates new timestamped directories, branch create errors when the branch already exists, and branch merge deletes the branch after mutating it. These are not idempotent behaviors.

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 long but justifiably so: 8 parameters and 6 distinct actions require this level of detail. It is organized into scannable sections, front-loaded with the core purpose, and every sentence contributes operational knowledge rather than padding.

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 the complexity of a six-action dispatcher with mixed read/write/destructive behavior, the description is essentially complete: it covers storage namespace, cross-session persistence, per-action side effects, error format, and exclusions. An output schema exists to carry exact return shapes, so no critical gap remains for correct invocation.

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%, so the baseline is 3. The description adds meaningful action-conditioned semantics: name is required only for read/write, label only for snapshot, content and artifact_type only for write, branch_name required for branch create/merge, and invalid action or branch_action values short-circuit before the backend call. This is selection guidance beyond the schema text.

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 opening sentence states a precise verb and resource: 'Unified context-filesystem entry point — dispatches to one of six actions.' It immediately describes the venture-scoped, versioned storage at ~/.delimit/context/<venture>/ and distinguishes itself from the delimit_context_* aliases and delimit_memory_* tools, so an agent knows exactly what this tool is and is not.

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 has explicit 'When to use' and 'When NOT to use' sections that name concrete alternatives: the specific delimit_context_<action> aliases, delimit_memory_store, and delimit_memory_search. It also explains the snapshot vs branch distinction and notes that this tool never touches git or a code repository.

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