mnema

Official

Overview Schema Source Related Servers Discussions Admin

Record an observation

record_observation

Record an observation about a task or decision in mnema's append-only chain, tied to the current agent and session, so decisions and context remain traceable.

Instructions

Record an observation ABOUT an entity (a task, decision, …) into the mnema chain, attributed to this agent and pinned to the current session. It carries the observed entity id (about), a short topic, and the observation text. The about id is NOT checked to exist: a reference to an entity in another tree is honest and resolved on read. Optionally pick the scope and the project it lands in; omitted, both follow the session default (private for an agent in a project, global outside one). Returns the observation’s own minted id, and says which tree it landed in. RECORDING IS PERMANENT: mnema is append-only and nothing deletes a fact. A record in the public scope is committed to the repository and reaches every machine that clones it (published, if that repository is public). So do NOT record credentials here. Values in a recognized format (cloud keys, API tokens, private keys, a password inside a URL) are replaced with a typed placeholder before anything is written and the reply says what was replaced, but a format mnema does not recognize is written verbatim and cannot be taken back. Do not record personal data either: an email address is replaced with and reported, and the mnid already says who wrote. Each text field holds at most 65536 bytes; a longer one is refused, not truncated.

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": {
      "about": "<about>",
      "topic": "<topic>",
      "text": "<text>"
    },
    "name": "record_observation"
  }
}

Input Schema

Name	Required	Description
`text`	Yes	The observation itself.
`about`	Yes	The id of the entity being observed.
`scope`	No	Where the observation lands; overrides the session default.
`topic`	Yes	A short topic label.
`project`	No	Which project of this workspace the fact belongs to: its absolute path, as this server gave it; a bare name is refused. Omitted, it lands in the project this session resolved to (the one `bootstrap` names). Pass it whenever the work being recorded happened in a different project of this workspace.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only say it is a non-destructive, non-idempotent write; the description goes far beyond that with append-only permanence, irreversible publication of public-scope records to every clone, typed placeholder substitution for recognized secret formats (and verbatim writing for unrecognized ones), email redaction, and a hard 65536-byte refusal rather than truncation. The disclosure that `about` is not existence-checked is exactly the kind of behavior an agent cannot infer from schema or 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?

Front-loaded with what it does, then payload, then defaults, then the safety/limits section — a sensible order with no filler sentences. It is dense and a few clauses run long (the scope-default parenthetical, the secret-format sentence), so it loses a point on scannability rather than on waste.

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 5-parameter, append-only write with no output schema, the description covers the missing pieces an agent would otherwise guess at: return value ('the observation's own minted id, and which tree it landed in'), scope/project defaults, input size ceiling, and full irreversibility/leak consequences. Nothing needed to call it safely is absent.

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 the baseline is 3; the description adds real meaning on top by explaining that `about` is deliberately unvalidated and may point into another tree, and by spelling out the scope/project default resolution (private for an agent in a project, global outside one). It adds nothing further on `topic` or `text` beyond the byte limit, which is minor given the schema already documents each field.

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?

Names a specific verb and resource ('Record an observation ... into the mnema chain') and immediately pins the shape: an `about` entity id, a `topic`, and the `text`. That framing separates it from the other write siblings (record_decision, record_handoff) whose payloads are presumably typed differently, and it states attribution and session-pinning up front.

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?

Gives clear exclusion criteria rather than inclusions: do not record credentials, do not record personal data, and pass `project` whenever the recorded work happened elsewhere. It does not explicitly name a sibling to use instead for decisions vs. observations, so the boundary with record_decision is left implicit; strong context, but no explicit alternative routing.

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