spec-gate

Overview Schema Source Related Servers Discussions Admin

Write the decision record

write_record

Store a committed decision record with evidence-scored dimensions, assumptions, and overrides, so the verdict is computed from declared coverage.

Instructions

Stores the decision as a committed record: what was missing, what was assumed, who authorised proceeding. The verdict is computed from the declared coverage, not accepted from the caller.

Input Schema

TableJSON Schema

Name	Required	Description
`cwd`	No
`target`	No
`request`	Yes	The request as received, verbatim.
`session`	No	Session id, so the pre-work hook can scope authorisation to this run.
`override`	No	Only to proceed below the threshold. The reason is stored verbatim and is not optional.
`dimensions`	Yes	One entry per profile dimension, scored against the rubric.
`assumptions`	No	Carried but not established. Listing them is what makes them visible.
`constraints`	No

Output Schema

TableJSON Schema

Name	Required	Description
`hash`	Yes
`path`	Yes
`vetoed`	Yes	Dimensions where a rule capped the declared score.
`missing`	Yes
`decision`	Yes
`threshold`	Yes
`sufficiency`	Yes
`markdown_path`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.0.1Sep 16, 2026

TDQS

B3/5.0

Behavior3/5

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

With no annotations, the description carries the burden. It discloses that the verdict is computed from declared coverage rather than accepted from the caller, which is a key behavioral trait. However, it omits details on side effects (e.g., persistence, idempotency) or error behavior, leaving gaps 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?

The description is two sentences, front-loaded with the core action, and contains no fluff. Every word contributes to understanding the tool's purpose and a critical behavioral detail.

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?

Despite having an output schema, the description is too sparse for a tool with 8 parameters, nested objects, and a sibling tool. It lacks usage context, parameter guidance, and behavioral completeness, leaving an agent with insufficient information to call it correctly.

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 63%, moderate. The description adds no parameter-level meaning; it does not explain the missing cwd, target, or constraints fields or clarify their roles. The schema provides descriptions for several fields, but the description fails to compensate for the uncovered parameters.

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?

The description clearly states the tool stores a decision record and lists what is recorded (missing, assumed, authorised). However, it does not differentiate from the sibling score_request, leaving the distinction to inference.

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

Usage Guidelines2/5

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

No guidance is given on when to use this tool versus score_request. The description implies it operates after scoring but provides no explicit when-to-use or when-not-to-use instructions.

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

Deploy Server