Accept or reject applied code edits to control each step. Rejection triggers automatic file rollback and routes feedback into the next attempt.
Accept or reject the applied edit for a step. Rejection rolls the files back; feedback goes to the next attempt.
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | ||
| step_id | Yes | ||
| verdict | Yes | ||
| feedback | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
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 behavioral disclosure burden. It explicitly reveals that rejection rolls files back and feedback is passed to the next attempt, providing important side-effect information. It does not describe acceptance behavior or permission requirements, but the key destructive behavior is transparent.
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?
The description is two sentences, front-loaded with the main purpose and immediate side effect. Every clause adds meaning without redundancy or filler.
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?
The tool has an output schema and simple parameters, but the description omits exact verdict values, which are critical for correct invocation. It also does not explain how run_id and step_id relate to the workflow, although their names are self-explanatory.
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%, so the description must compensate. It clarifies that verdict means accept or reject and feedback goes to the next attempt, but it does not specify exact accepted verdict string values or formats for run_id and step_id beyond their names.
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 clearly states the tool accepts or rejects an applied edit for a step, which is a specific verb and resource. It distinguishes itself from siblings like bicameral_review_diff (viewing a diff) and bicameral_critique (providing critique) by naming the decision action.
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 description implies usage after an edit is applied by mentioning rejection rolls files back and feedback goes to the next attempt. However, it does not explicitly name alternatives or state when not to use this tool versus bicameral_review_diff or bicameral_critique.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.