Skip to main content
Glama

remember_decision

Record decisions with rationale and context so later recall answers what was decided and why. New decisions on a topic supersede old ones, keeping decisions current, correctable, and revertible.

Instructions

Store a DECISION — the thing that actually matters and that a raw event/command log misses. Use this whenever you (or the user) CONCLUDE or CHOOSE something: "we decided X", "we're going with Y", "dropped Z", "the plan is W". Pass because (the rationale) and context (the situation) — they're kept for retrieval so a later recall answers "what did we decide, and why", not just "what commands ran".

topic (recommended) gives the decision deterministic keyed supersession (decision::<topic>): a NEW decision on the same topic RETIRES the old one, recall returns the CURRENT decision, and revert('decision::<topic>') restores the prior one — decisions stay current, correctable, revertible, and auditable, with NO LLM and no similarity guesswork (inspeximus's integrity moat applied to decisions; an LLM-extracted fact store can't do this).

source / derived_from — same meaning as on remember, and they matter MORE here, not less. A decision is usually ABOUT someone ("we're billing Alice monthly"), which makes it exactly the kind of record a right-to-erasure request has to reach. Without a source it is attributable to nothing but its own id: forget_subject cannot find it, and it survives a DSAR that erased everything else about that person. Measured: a decision written with no source answered would_erase=0 to every phrasing of the subject.

If this server was started with a PROJECT scope, the decision is stamped with it — so "we're going with Postgres here" recorded in one repo does not surface while you work in another. NOTE that the supersession key stays decision::<topic> and is NOT namespaced by project: the same topic in two projects still supersedes across them. Use a project-qualified topic when you want them independent.

Returns the new memory id and the verdict on the write (blocked, policy, current_id, lineage_dropped), as remember does.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topicNo
sourceNo
becauseNo
contextNo
decisionYes
derived_fromNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.20.1

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly: it discloses deterministic supersession via `decision::<topic>`, retirement of old decisions, `revert` behavior, project-scope stamping with the non-namespaced supersession caveat, and the erasure implications of omitting `source`. It also states the return payload (id plus write verdicts), leaving little unstated about side effects or statefulness.

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 long but densely packed with essential semantics: use case, supersession mechanics, project-scope caveat, and erasure behavior. It is front-loaded with the primary purpose and then adds detail in a logical order. A few phrases ("inspeximus's integrity moat applied to decisions") are somewhat promotional, but they do not dilute the operational guidance enough to drop the score further.

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 six parameters, no annotations, and no output schema, the description is remarkably complete. It explains when to use the tool, what each parameter does, how supersession and revert work, how project scoping interacts with topics, how source/derived_from affect erasure compliance, and what the return value contains. An agent has everything needed to invoke it correctly and anticipate side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain the parameters itself. It does: `topic` is tied to keyed supersession and is recommended, `because`/`context` are described as retained rationale/situation for later recall, and `source`/`derived_from` are explained with respect to forget_subject and DSAR reachability. Even the required `decision` is contextualized by the tool's purpose, giving every parameter meaning beyond its name.

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 opens with a specific verb-resource pairing: "Store a DECISION" and immediately contrasts it with "a raw event/command log misses," which distinguishes it from the sibling `remember`. It also provides concrete decision examples ("we decided X", "we're going with Y", "the plan is W"), leaving no ambiguity about what the tool is for.

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 is explicit about when to use the tool: "Use this whenever you (or the user) CONCLUDE or CHOOSE something," with examples covering several decision phrasings. It implies the alternative is `remember` for raw events, and it explains when `source`/`derived_from` matter more, but it does not explicitly say "do not use this for raw events" — the boundary is clear but implied rather than stated as an exclusion.

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