pbi_recover_from_journal

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag destructiveHint=true, but the description adds substantial behavior: preview mode without confirm, the five possible states, rejection on changed files via `recovery_conflict`, the `force_conflict` override, byte-by-byte verification, and recreation of missing parent directories. It also reveals that conflicts prevent overwriting work, which is critical safety information.

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 compact, well-structured, and front-loaded with the core action and a warning. Every sentence adds value: preview behavior, conflict details, safety checks, and directory restoration. No filler or repetition.

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?

Given the tool's destructive nature, the description covers all essential aspects: preview, execution, conflict resolution, verification, and side effects on parent directories. Since an output schema exists, return values are already structured. The description is complete enough for an agent to decide safely.

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 0%, so the description must define parameter meaning. It clearly explains `confirm` (preview vs execution) and `force_conflict` (apply despite a conflict). `journal` is implicit in the tool purpose. However, `request_id` is not explained at all, leaving one parameter's semantics unclear.

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 starts with 'Restaura los originales guardados en un journal' — a specific verb and resource. It clearly distinguishes this tool from siblings like pbi_inspect_journal (inspect only) and pbi_purge_backups (permanently delete). The 'DESTRUCTIVA' marker reinforces its purpose as a recovery/restore operation.

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 explicitly explains the preview mode (without `confirm`) versus the actual recovery (with `confirm`), and how `force_conflict` handles conflicts. This gives clear context for when to use each parameter. However, it does not name alternative tools or state when not to use this tool, so it stops short of a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.