Report the ADR-006 baseline judgment for a codebase. It returns score, ratchet status, and axes without writing a baseline.
ADR-006 baseline judgment: score, ratchet and axes (report only — this surface never writes a baseline).
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | churn window in days; absent = the churn tables stay empty | |
| path | No | subpath (default: project root) | |
| floor | No | arm the --fail-under score floor; absent = the ratchet alone judges |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present the description carries the full burden, and it does disclose one meaningful trait: this surface is non-mutating and never writes a baseline. Beyond that it says nothing about permissions, what the 'ratchet' or 'axes' output means, or failure behavior, so the disclosure is thin for an unannotated tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
It is a single dense sentence with no padding, and the report-only caveat is placed at the end as a qualifier. It is efficient, though the jargon makes it less immediately readable than it could be.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, a report-generating tool of this apparent complexity should explain what it returns and what the score/ratchet/axes concepts mean. The description leaves the agent guessing at the result shape and the semantics of its own domain terms.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and all three parameters (days, path, floor) are documented in the schema, including absence semantics — so the baseline is 3. The description adds no parameter-level meaning beyond that.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description leans on internal jargon ('ADR-006 baseline judgment', 'ratchet and axes') and never states a plain verb+resource an agent can act on. It never distinguishes itself from close siblings such as trend, scan or update_check, several of which plausibly also report baseline-ish status. An agent can't confidently tell what 'check' actually computes from the text alone.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is a partial exclusion — 'report only — this surface never writes a baseline' implies when not to reach for a writing surface — but no positive guidance on when to choose this over trend, scan or architecture. No prerequisites or trigger conditions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.