Checks the recorded status of a previously previewed edit by edit ID, returning preview, applied, undone, or uncertain as a session receipt rather than a fresh property read.
Read a session edit record (preview/applied/undone/uncertain). This is a receipt, not a fresh property read. Records expire on bridge restart.
| Name | Required | Description | Default |
|---|---|---|---|
| editId | Yes | Token returned by editor_preview_edit; never invent one. |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: the record is a point-in-time receipt rather than live state, and records expire on bridge restart, which is critical for interpreting 'uncertain' or missing results.
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, front-loaded with what is returned, then the receipt caveat, then the expiry constraint. No redundant restatement of the tool name or annotations.
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, the description does the work of explaining that the result is a state enum plus receipt semantics, and warns about restart-scoped expiry. Slightly incomplete on what else the record contains (e.g., timestamps, error detail), but sufficient to call and interpret the tool.
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 coverage is 100% and editId already carries a strong description ('Token returned by editor_preview_edit; never invent one'). The tool description adds no further semantics about the parameter, so baseline 3 applies.
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 concrete verb and resource ('read a session edit record') and enumerates the possible states returned (preview/applied/undone/uncertain). The clause 'This is a receipt, not a fresh property read' explicitly separates it from sibling property-read tools like editor_read_member and editor_read_entry.
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?
Usage is only implied: read the receipt of an edit after preview/apply/undo. The description supplies a useful exclusion ('not a fresh property read') but never names editor_status or editor_preview_edit as the alternative, leaving the boundary with the similarly named editor_status unresolved.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.