Skip to main content
Glama

Memory

memory
DestructiveIdempotent

Read or overwrite this workspace's handoff note at /.venira/memory.md (action=read|write; write replaces it all, max 6000 bytes).

Instructions

Read or overwrite this workspace's handoff note at /.venira/memory.md (action=read|write; write replaces it all, max 6000 bytes). Use when: a task starts or resumes (read, after recent_files); before you finish or run out of context (write: goal, decisions, files touched, next steps). Avoid when: lasting docs (write_file) or history (git_log). Plain text on disk: no secrets. Output: read: exists, content, bytes, updated_at_ms. write: replaced, previous_bytes, bytes, updated_at_ms. Over the cap or empty content: invalid_request, old note kept.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesread: return the saved note (exists=false + hint when none). write: replace it entirely with `content`.
contentNowrite only: the full new note (markdown, max 6000 bytes). Replaces the previous one; empty/missing content is refused.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv4.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations it discloses that write replaces the entire note, the 6000-byte cap, that content is plain text on disk with no secrets, and the failure mode (over cap or empty content -> invalid_request, old note kept). It also enumerates return fields for both actions, which annotations alone cannot convey.

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?

Front-loaded purpose sentence, then labelled Use when / Avoid when / Output / error blocks. Every line carries actionable content with no filler, and the output listing is compact.

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?

With no output schema, the description supplies the return shape for both actions plus the error contract, and covers the mutation risk and size limit. An agent has everything needed to call it correctly on the first attempt.

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% and the enum descriptions already explain read vs write and the replacement behavior, so the description largely restates that. It adds only the byte cap framing in the parenthetical, which is marginal over the existing 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?

States a specific verb pair (read/overwrite) and a specific resource (this workspace's handoff note at <workspace>/.venira/memory.md), including the exact path and the size cap. It is immediately distinguishable from siblings like write_file or git_log because it is scoped to a single handoff note.

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?

Explicit 'Use when' covers both entry points (task start/resume -> read, after recent_files; before finishing/out of context -> write) and 'Avoid when' names concrete alternatives (write_file for lasting docs, git_log for history). Nothing is left to inference.

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