Runs the CI accuracy gate by testing every positioning scenario and preset against the regression baseline, with configurable seeds, to catch accuracy regressions.
Run the CI accuracy gate: every scenario and preset against tests/regression/baseline.json.
| Name | Required | Description | Default |
|---|---|---|---|
| seeds | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose real scope ('every scenario and preset'), which signals a broad, expensive operation, but says nothing about runtime, whether failures abort the run, what artifacts are written, or whether it mutates any state. Too thin for an unannotated whole-suite execution 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?
One sentence, front-loaded with the action and immediately scoped. No filler. It is efficient, though the terseness is partly the cause of the gaps elsewhere.
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?
A whole-suite accuracy gate with no output schema and no annotations needs the description to explain the pass/fail contract and the seed parameter. Neither is covered, so the agent cannot predict the result shape or the cost of a larger seed count.
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?
The single parameter 'seeds' has 0% schema description coverage and is never mentioned in the description. The agent must guess that increasing seeds means more repetitions per scenario and what the cost tradeoff is. One undocumented parameter pulls this below the zero-param baseline.
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?
Specific verb+resource: it runs the CI accuracy gate over every scenario and preset against a named baseline file. That clearly separates it from simulate_scenario, run_replay and ab_test, which operate on targeted cases. It stops short of naming a sibling, but the scope statement does the differentiation work.
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?
'CI accuracy gate' implies the when: an all-up correctness check rather than an exploratory run. No explicit exclusion, no statement of when a targeted replay/simulation is preferable, and no prerequisite is stated. Usage is inferable but not spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.