Preview or persist a locator-only patch for a failing test step, with backup and audit log, then rerun the suite to verify. Cannot modify assertions or expected values.
Preview or persist a locator-only patch in a suite, with a backup and audit log. Cannot modify assertion steps or expected values. Rerun the patched suite to verify.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| apply | No | ||
| testId | Yes | ||
| locator | Yes | ||
| stepIndex | Yes |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds real context the agent could not otherwise know: a backup and audit log are created, and assertion steps or expected values cannot be modified. That materially scopes the blast radius of a destructive operation. It still omits what the preview returns or what happens when the locator fails.
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?
Three short sentences, zero filler, with the core action and its preview/persist duality front-loaded. Every sentence carries distinct information (capability, scope limit, verification step).
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?
For a destructive mutation tool with no output schema and a rich nested locator schema, the description covers intent and safety but not the shape of a preview result or failure behavior. An agent still doesn't know what 'preview' returns or how to interpret a rejected patch.
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 0% across 5 parameters, including a nested locator object with twelve undocumented fields. The description hints at the locator ('locator-only patch') and at the apply flag ('preview or persist'), but leaves path, testId, stepIndex, and every locator strategy field (css/role/text/frame/etc.) unexplained, so it does not compensate for the coverage gap.
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?
States a specific verb pair (preview/persist) and resource (a locator-only patch in a suite), which is concrete enough to distinguish it from siblings. It does not explicitly name heal_suggest as the alternative, so sibling differentiation is implied rather than stated.
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?
The preview-vs-persist distinction implies a workflow and the closing line 'Rerun the patched suite to verify' gives post-call guidance. However, it never says when to call this versus heal_suggest, nor when not to use it, so usage must be inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.