Alethea

Record decision or constraint

record_decision

Record ADR-style decisions and machine-checkable constraints in .decisions/ after a non-obvious choice, keeping project rationale and rules linked for future agents.

Instructions

Record an ADR-style decision (or a constraint with type="constraint") into .decisions/. Call after making a non-obvious choice.

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": "record_decision"
  }
}

Input Schema

Name	Required	Description
`tags`	No
`type`	No
`files`	No	Paths or globs this applies to
`rules`	No	Constraint rules: "forbid: term", "forbid: /regex/", "require: term", "forbid-path: glob"
`tests`	No
`title`	Yes	Short title of the decision or constraint
`status`	No
`commits`	No
`context`	No
`decision`	No	What was decided / the constraint statement
`supersedes`	No
`alternatives`	No	Options considered and rejected
`consequences`	No
`requirements`	No	SpecGate ids: capability/requirement[#scenario]

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 19, 2026

TDQS

B3/5.0

Behavior2/5

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

With no annotations, the description carries the full behavioral burden but only discloses the write destination (.decisions/) and ADR framing. It omits whether existing decisions are overwritten, permission/auth needs, reversibility, or side effects from constraint rules – all material for a mutation tool.

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?

Two tightly-packed sentences with the action and destination front-loaded and zero filler. Nothing needs trimming and the constraint/decision distinction is stated up front.

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

Completeness2/5

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

For a 14-parameter mutation tool with no annotations and no output schema, the description is far too thin. It gives no guidance on the ADR field set, the constraint rules syntax, or how this relates to supersede_decision, so an agent cannot fully populate or route the call from the description alone.

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

Parameters2/5

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

Schema description coverage is 43%, below the 50% threshold, so the description should compensate but instead only references the type enum and implicitly title. It adds no meaning for the other twelve parameters (context, decision, alternatives, consequences, rules, requirements, status, tags, supersedes, etc.), leaving constraint-specific fields unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb (Record), resource (ADR-style decision / constraint), and destination (.decisions/), and distinguishes the two modes via type="constraint". It stops short of differentiating from siblings like supersede_decision or list_constraints, so an agent must infer the boundary.

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

Usage Guidelines3/5

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

"Call after making a non-obvious choice" gives a clear triggering condition, which is more than nothing. However, it offers no exclusions and no routing to alternatives such as supersede_decision (for replacing an existing ADR) or link_requirement, which are likely relevant given the sibling list.

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

Deploy Server