Weft

Record a Decision

record_decision

Two uses, one table of record.

(1) RELAY A VERDICT the user just gave in conversation about work waiting on them — 'approved', 'redo it with X', 'drop that one'. Pass id + decision (+ note in their words). It clears the task from the review queue. Never call this to accept your own work: you are the messenger, not the decider, and 'the user did not object' is not a decision.

(2) RECORD A DECISION WORTH REMEMBERING — 'chose Neon over Supabase', 'dropped the referral program', a lesson learned. Pass title + outcome, plus whatever MADR context you have (context, options weighed, consequences, confirmation = the condition to revisit under). Records are immutable; to change one, record a new decision with supersedesId pointing at it. Use it whenever the user makes a real choice in conversation — the reasoning otherwise dies in scrollback, and decisions are what agents read next week via get_context.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	No	Task ID — verdict relay only
`kind`	No	'madr' (default) for a decision; 'lesson' for a lesson learned.
`note`	No	What the user said, in their words. Required in substance for rework — the executor has to act on it.
`title`	No	Standalone record: the decision, named. E.g. "Postgres provider: Neon".
`status`	No	Defaults to 'accepted'. 'proposed' = written down before the user has committed.
`taskId`	No	A task this standalone decision is about, if any.
`context`	No	What was true that forced a choice.
`options`	Yes	The options actually weighed — not a retrofit.
`outcome`	No	Standalone record: the choice, stated as a sentence. Required with title.
`project`	No	Project name (case-insensitive) or project ID
`decision`	No	Verdict relay only — what the user said: 'accepted' the work stands; 'rework' send it back (say why); 'dropped' not worth doing; 'deferred' fine but not now.
`confirmation`	No	The condition under which to revisit this decision.
`consequences`	No	What follows from the choice, good and bad.
`supersedesId`	No	A prior decision this one replaces. The old record stays, marked superseded.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 16, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations only say the tool writes but is not destructive. The description adds crucial behavioral context: records are immutable, changes require a new record with supersedesId, verdict relay clears the task from the review queue, and the agent is 'the messenger, not the decider'. This goes well beyond the structured hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but tightly structured with numbered modes, bolded labels, and scannable examples. Every sentence adds operational value for a complex 14-parameter tool; there is no filler.

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?

The description is nearly complete for a dual-mode write tool, covering triggers, side effects, immutability, and downstream consumers like get_context. However, the schema marks options as the only required parameter, yet the description's verdict-relay path never instructs the agent how to satisfy that requirement, so a faithfully-following agent could build a call that fails validation.

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 100%, but the description adds a conceptual layer the schema lacks: it groups id/decision/note as the verdict-relay path and title/outcome/MADR fields as the standalone-record path. It also sharpens semantics for supersedesId and warns that options weighed must not be a retrofit.

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 'Two uses, one table of record' and clearly enumerates both: relaying a verdict from conversation and recording a standalone decision worth remembering. This gives a specific verb and resource for each mode and distinguishes the tool from siblings like create_task and update_task.

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?

Provides explicit triggers ('whenever the user makes a real choice in conversation') and explicit exclusions ('Never call this to accept your own work', 'the user did not object is not a decision'). It also clarifies when each of the two modes applies, leaving no ambiguity about selection.

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

All Weft tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?