apply_changes

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

Goes well beyond the annotations (destructive/non-idempotent/non-read-only) by disclosing the concrete side effects: OpenDeck is stopped, a backup is made, all staged changes are written, verified, then the app restarts. An agent understands exactly what state will be mutated and that a restore path exists.

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?

Two tight sentences with the identifying claim and the full effect sequence front-loaded, followed by the safety-critical call pattern. No filler.

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?

An output schema exists so return values need not be described, and the annotations plus prose cover the safety profile and workflow. The remaining gap is behavioral meaning for on_conflict and allow_untested_version, which an agent would have to infer.

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 50%; confirm and show_window already have descriptions, and the prose reinforces confirm=false as the dry-run. However on_conflict (abort/skip) and allow_untested_version are undocumented in both schema and description, so the description does not 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 operation ('changes OpenDeck') and enumerates the exact workflow: stops, backs up, writes staged changes, verifies, restarts. 'The only tool that changes OpenDeck' directly differentiates it from siblings like preview_changes, discard_changes and stage_plugin.

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 an explicit two-step usage pattern ('call with confirm=false first and show the user the result'), which is clear precondition guidance. It does not explicitly name sibling alternatives (e.g. preview_changes), but the 'only tool that changes' framing and the dry-run-then-apply flow cover the practical decision well.

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