Skip to main content
Glama

backlog_remember

Record stable facts, procedures, or preferences to recall in future sessions. Correct or update existing knowledge by superseding or state keys.

Instructions

Write a durable memory — a stable fact, a procedure, or a preference you should know next session. Use when you learn something worth keeping: "this repo deploys via wrangler", "Goga prefers terse evidence bullets". To CORRECT existing knowledge, pass supersedes (the old MEMO- id is expired, lineage kept) or state_key (previous holders of the same evolving fact are closed). The optional collision_candidates receipt is tri-state: [] means the advisory scan completed clean; a non-empty array means nearby facts deserve adjudication; absent means the advisory scan did not run or failed, not that the write failed. Do not use for task events — completions are captured automatically.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
asNoOPTIONAL agent identity for this write — an AGENT- doc id or declared principal (e.g. "aime:granite"). Values are trimmed; whitespace-only is treated as absent.
homeNoSelect the document home for this call. Overrides bridge defaults: global uses the user-wide home; project uses project_root or the bridge project.
kindNoTemporal kind: current fact / historical fact / future plan / preference / timeless (exempt from recency decay).
tagsNoFreeform labels for filterable recall.
layerNosemantic = stable fact (default). procedural = how-to/process. episodic = a specific event worth keeping.
titleYesMemory title (required, like a task title) — a short human-readable label for the fact. Title and body are both first-class.
contentYesThe memory body (markdown) — the fact itself.
contextNoScope container id (e.g. "FLDR-0001") — enables scoped recall and wakeup.
derivedNoMark as inference (consolidator output). Requires non-empty entity_refs citing the sources.
state_keyNoEvolving-fact key (e.g. "build.bundler"). Storing a new memory with an existing key closes the previous holder.
supersedesNoMEMO- id this memory replaces. The predecessor is soft-expired.
entity_refsNoSource entities this knowledge derives from (e.g. ["TASK-0676"]).
occurred_atNoWhen the remembered event occurred — ISO date/datetime. Decay uses this instead of write time.
valid_untilNoExpiry — ISO date/datetime. After this the memory drops out of recall.
project_rootNoProject root for this call. Overrides the bridge project root and selects the project home.
Behavior5/5

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

With no annotations provided, the description fully carries the burden. It explains the tri-state collision_candidates receipt, how supersedes soft-expires predecessors, and that state_key closes previous holders. This goes beyond the schema to disclose behavioral traits.

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 description is around 150 words and front-loaded with the core purpose. It is informative but slightly dense as a single paragraph; bullet points could improve scannability. Nonetheless, every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 15 parameters and no output schema, the description covers key behaviors (writing, correcting, receipt handling, scope) but doesn't detail the return value or error cases. It is mostly complete, leaving only minor gaps.

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 baseline is 3. The description adds significant value by explaining the tri-state collision_candidates, how supersedes and state_key work, and giving usage examples, which enhances understanding beyond the 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 states 'Write a durable memory' with concrete examples like 'this repo deploys via wrangler', which is specific. It distinguishes from siblings by explicitly saying 'Do not use for task events — completions are captured automatically' and mentioning how to correct knowledge, differentiating it from other write tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly says 'Use when you learn something worth keeping' and warns not to use for task events. However, it does not directly compare with alternatives like backlog_capture_reference or backlog_capture_requirement, though it implies its scope is durable facts.

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/gkoreli/backlog-mcp'

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