audit_replay

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is covered. The description usefully adds that entries are filtered by identity and policy validation and that only safe entries are replayed, but it omits what gets destroyed, that a confirmation token is required, and whether the preflight itself is harmless.

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?

A single front-loaded sentence with no filler, leading with the dry-run action before the optional mutation. The density of undefined jargon costs it a point, but every clause does work.

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, non-idempotent, open-world tool with no output schema and half-documented parameters, the description should at minimum explain the preflight/replay distinction and the confirmation requirement. It does not, leaving an agent unable to call it safely with confidence.

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 only 50%; only confirmation_token and max_record_age_seconds carry descriptions. The description adds no semantics for 'execute' or 'allow_clipboard', does not explain that execute toggles the replay hinted at by 'optionally', and leaves the 300s default age window unexplained in prose, so it fails to 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 ('preflight' the redacted audit journal, 'optionally replay') and a specific resource, which clearly separates it from the UI-automation siblings. However 'preflight' and 'replay' are nonstandard jargon that the description never defines, leaving some ambiguity about what is actually read versus written.

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 word 'optionally' implies a mode switch but never says when to actually enable replay, when to stay in preflight, or what the conditions are that make an entry 'safe'. No prerequisites, no mention of the confirmation flow, and no alternatives are named.

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