Force-push a squashed snapshot to a mirror remote (destructive)

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

The description goes well beyond the destructiveHint annotation by explaining the two-signal confirmation (dry_run=False AND confirm=True), the default dry-run behavior, and the explicit warning about history-rewriting. This is critical operational detail that prevents accidental destructive actions. No contradiction with annotations.

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 yet detailed, front-loading the core action before explaining the confirmation logic. The length is justified by the safety-critical nature of the operation. No fluff, though it could be slightly tightened by removing the CLI reference.

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 complexity and destructive nature, the description covers the essential operational context: default dry-run, confirmation requirement, and the fact it rewrites history. The output schema is present (not shown) so return values are likely covered. It does not explain 'squashed snapshot' or 'tracked content', but these are domain-specific and acceptable.

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 thoroughly explains dry_run and confirm, including their interplay. However, it leaves branch, remote, exclude, and message unexplained; though these are fairly self-explanatory from names and defaults, the description does not add value for them. Partial compensation.

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 verb (force-push), resource (a single-commit snapshot), and target (a secondary/mirror remote). It distinguishes itself from sibling tools like validation or health checks by emphasizing the destructive publish action. The title adds further clarity with 'destructive' and 'mirror remote'.

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 provides strong context about when to use it (publishing a snapshot) and implicitly contrasts with non-destructive tools like rrt_validate_branch or rrt_health. It does not explicitly name alternatives or state 'when not to use', but the destructive nature and unique purpose make the intended usage clear.

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