Delete the edit history

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

Annotations already declare destructiveHint=true, so the bar is lower, yet the description adds substantial context: exactly what is destroyed (the edit journal plus the backup files undo_edit relies on), where they live (MB2_DATA_DIR), that the loss is irreversible, and that confirmation is mandatory. It also clarifies that screenshots/traces in the bridge folder are not covered here.

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?

Front-loaded with the action and its scope, then consequences, then the confirm gate, with the cleanup cross-reference placed last where it doesn't interfere. Dense but every clause carries weight; the stacked parenthetical paths make it slightly harder to scan than it needs to be.

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 tool with full annotation coverage, a fully documented 2-parameter schema, and no output schema, nothing an agent needs is missing: target, scope, irreversibility, confirmation requirement, and where the related-but-unhandled artifacts are cleaned up.

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%, so both parameters are already documented, and the description largely restates them ('Needs confirm=true', 'default: all'). It adds the consequence framing for confirm, but no syntax or edge-case detail beyond the schema, so the 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 specific verb and resource ('Deletes this server's edit journal and the file backups it keeps for undo_edit'), scopes it ('all of it, or only edits older than older_than_days'), and ties it to the sibling undo_edit it feeds. An agent can distinguish it from edit_history and undo_edit without opening any schema.

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?

Gives clear context: this is the irreversible cleanup path ('Forgotten edits can no longer be undone') and requires confirm=true, while routing the adjacent-but-different cleanup (screenshots/traces) to editor_command action=cleanup. It never states the explicit alternative 'use undo_edit instead if you want to revert', so it stops short of full when-not guidance.

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