Skip to main content
Glama

delimit_memory_index

Write flagged hot memory entries into Claude Code's MEMORY.md to load them automatically on session start. Only the marked section is replaced, preserving existing content.

Instructions

Project delimit_memory hot entries into Claude Code's MEMORY.md.

When to use: to surface hot delimit_memory entries (flagged hot_load=True) into Claude Code's MEMORY.md so they load on session start without making delimit_memory dependent on Anthropic's auto-memory format. When NOT to use: to add a new memory (use delimit_memory_store) or search existing memories (delimit_memory_search, delimit_memory_recent).

Sibling contrast: delimit_memory_store writes a new entry; delimit_memory_search queries; delimit_memory_recent returns the tail; this is the one-way projection into MEMORY.md.

Side effects: writes to target_path (default ~/.claude/projects/-root/memory/MEMORY.md). If the file already has <!-- delimit:start --> / <!-- delimit:end --> markers, ONLY the content between them is replaced; anything outside is preserved. If markers are missing, the managed section is APPENDED to the end of the file (existing content is never touched). If the file does not exist, it is created with just the section. One-way projection only — MEMORY.md is never read back into delimit_memory (Anthropic owns the auto-memory format; format-drift risk).

LED-1165 Phase 2 #5 PR-B.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
target_pathNofile to write. Empty = default ~/.claude/projects/-root/memory/MEMORY.md.
dry_runNoTrue returns the rendered content size without writing.
limitNocap on entries projected. Default 200.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

No annotations exist, so the description fully covers behavioral traits: it details side effects (file writing, marker replacement, appending, file creation) and risks (one-way projection, format-drift). No contradictions with missing annotations.

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 clear sections, but includes a trailing line 'LED-1165 Phase 2 #5 PR-B.' that is irrelevant for the agent and slightly reduces conciseness. Otherwise, front-loaded with purpose and logically organized.

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 tool's complexity (file projection with conditional behavior) and no output schema shown (though context says it exists), the description is complete. It explains all key behaviors, edge cases, and constraints, leaving no critical gaps for selection or 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?

Input schema covers 100% of parameters with descriptions. The description adds value by explaining how parameters interact with behavior (e.g., dry_run returns size, target_path default, limit cap). Still, the schema already provides basic semantics, so a 4 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?

Clearly states the tool projects hot delimit_memory entries into MEMORY.md, with a specific verb and resource. Distinguishes from siblings like delimit_memory_store, delimit_memory_search, and delimit_memory_recent by explaining its unique one-way projection purpose.

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' and 'When NOT to use' sections, naming alternative tools for adding new memories or searching. Also includes a sibling contrast paragraph that clarifies the different roles of related tools.

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