Skip to main content
Glama
Sign In
FlowState by DialectForge

FlowState by DialectForge

Official
by dialectforge
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

manage_memory

Destructive

Maintain shared memory hygiene: flag duplicate, stale, or misfiled records as suggestions, import memory exports, mark facts rechecked, correct sources, and safely delete user-requested entries.

Instructions

Memory upkeep. cleanup: queue likely duplicate, stale and misfiled records as suggestions (rejected ideas not repeated). import: a memory export (Claude, ChatGPT) or edited FlowState markdown into the review queue. stale: facts (paths, ports, URLs, config) unchecked for 60+ days (read-only). mark_checked: you re-checked one. set_source: correct an origin (user_stated waits for the user). delete: only when the user asks; deletes one record (and its attempts or links) after a safety copy, undo restores it; with approvals on it waits for the user's approve (manage_review). A changed fact is log_work. Requires project. Returns counts and ids, {facts} or the result.

Input Schema

NameRequiredDescriptionDefault
daysNostale: unchecked for this many days. Default 60.
kindNoimport (memory format): record kind for each memory. Default learning.
textNoimport: the file contents. Max 200,000 chars.
kindsNocleanup: which checks. Omit for all three.
limitNostale: max facts. Default 20.
modelNoModel name if known. Never guess.
actionYesThe operation; see the tool description.
formatNoimport: memory (default; one memory per line or bullet) or flowstate_markdown (an edited `flowstate export-md` file).
originNoimport: where it came from, such as Claude or ChatGPT.
sourceNoset_source (required) / mark_checked (optional): user_stated, ai_inferred or from_code.
projectYesProject name or id. Required.
record_idNodelete / mark_checked / set_source: the record's id.
record_typeNodelete / mark_checked / set_source: the record's type (the last two: todo, decision, change, learning, problem, variable, method).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.4.3
    • changedInput schema / properties / model / description
      Previous value: -"Your model name if you know it. Never guess."New value: +"Model name if known. Never guess."
  2. Addedv2.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations, the description discloses key side effects: cleanup queues suggestions and does not repeat rejected ideas, stale is read-only, and delete creates a safety copy with undo while cascading to attempts/links. It also notes approval gating for deletes and that set_source with user_stated waits for the user, all consistent with destructiveHint=true.

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?

The definition is front-loaded and every clause carries operational information, with no filler. It is dense and semicolon-packed rather than cleanly bulleted, which makes scanning slightly harder for a six-action tool, but the size is appropriate.

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?

For a complex multi-action mutation tool, the description covers action routing, prerequisites, safety behavior, approval behavior, and return shape. Although there is no output schema, it states that returns include counts and ids, {facts}, or the result, which is sufficient context 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 defaults and formats are already documented. The description still adds important meaning for the action enum and maps actions to relevant parameters, e.g. cleanup to duplicate/stale/misfiled checks, stale to 60+ days, import to memory exports or FlowState markdown, and delete to record identity.

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 names six concrete actions and what each does: cleanup queues duplicate/stale/misfiled suggestions, import ingests memory exports, stale reads unchecked facts, mark_checked updates a fact, set_source corrects provenance, and delete removes a record. It also distinguishes sibling tools by routing changed facts to log_work and approval waits to manage_review.

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?

Usage conditions are explicit for each action: cleanup handles likely duplicates/stale/misfiled items, stale targets facts unchecked for 60+ days, delete is only when the user asks, and changed facts belong to log_work. The description also states that set_source may wait for user input and that deletes may wait for approval via manage_review.

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

Deploy Server

Other Tools