mnema

Official

Overview Schema Source Related Servers Discussions Admin

Create a task

create_task

Open a trackable task in the mnema decision record with a title, optional scope, project, and description; it starts in the workflow's initial state for later transitions.

Instructions

Open a task in the mnema chain, attributed to this agent and pinned to the current session. A task needs a title; it starts in the workflow’s initial state and is moved from there with task_transition. Optionally pick the scope it lands in: public (team-visible), private (this machine, this project), or global (personal, cross-project); omitted, a task is the team’s work board and lands PUBLIC: committed, so a clone has the board (global outside a project). Optionally pick the project it lands in, when the workspace holds more than one. Optionally give a description (up to 64 KiB of text, refused beyond it): what the task is, recorded in the same call as an observation about it (topic description) whose id the reply names. Returns the minted id (the key to move it), the short alias a human reads, and 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": {
      "title": "<title>"
    },
    "name": "create_task"
  }
}

Input Schema

Name	Required	Description
`scope`	No	Where the task lands; overrides the routing rule (public).
`title`	Yes	What the task is.
`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.
`description`	No	The task in prose; recorded as an observation about it.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses that records are append-only and permanent, that public-scope records are committed and reach every clone (published if the repo is public), that recognized secret formats and email addresses are replaced with typed placeholders and reported, and that unrecognized formats are written verbatim and unrecoverable. It also states the initial workflow state and the return payload (minted id, short alias, target tree). The permanence warning sits in mild tension with destructiveHint=false, but creation does not destroy data, so this is added context rather than a contradiction.

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 the action, then defaults, then the safety warning — a sensible order for a permanent-write tool. It is long, and the 64 KiB cap is stated twice (once on description, once as a closing sentence about all text fields), which is minor redundancy rather than padding.

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?

There is no output schema, so the description supplies the return shape itself (minted id, alias, tree). For a non-idempotent, permanent write tool it covers defaults, project resolution, size limits, redaction behavior, and irreversibility — everything an agent needs to call it safely.

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 coverage is already 100%, yet the description still adds real meaning: it explains what each scope enum value means in practice (team-visible, this machine/project, personal cross-project) and the default routing rule, clarifies that project must be an absolute path rather than a bare name, and specifies that description is stored as an observation with topic 'description' whose id appears in the reply. That is meaning the schema does not carry.

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?

Opens with a specific verb and resource ('Open a task in the mnema chain'), names the attribution and session pinning, and explicitly distinguishes itself from the sibling task_transition ('moved from there with task_transition'). An agent can tell what this creates versus what moves it without reading any schema.

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 concrete selection guidance for the optional parameters: scope defaults to PUBLIC committed team board, private is this machine/project, global is personal cross-project; and project should be passed 'whenever the work being recorded happened in a different project of this workspace.' It routes state changes to task_transition. It stops short of naming when NOT to use this tool (e.g., versus record_observation for a non-work-item note), so it is clear context rather than full when/when-not guidance.

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