Repair Store Application

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

Beyond the destructiveHint=true annotation, the description discloses concrete behavior: it runs whatever the application's install runs, customized instance files are preserved and reported as skipped, refusal conditions, and how to interpret success ('Trust only a result that says Repaired'). The timeout note explains that a client giving up does not stop the repair and points at sys_execution_tracker to check it afterward—exactly the kind of operational context annotations cannot convey.

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 core action and its non-destructive-to-customizations caveat are front-loaded, and each subsequent sentence adds a distinct fact (refusals, success criteria, timeout behavior). It is dense and runs long as a single block, but no sentence is redundant.

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?

This is a destructive, long-running, open-world mutation with no output schema, so the description must carry result interpretation—and it does by defining what 'Repaired' means (tracker success plus a new upgrade history) and how to recover if the client times out. Combined with refusal conditions and skipped-file reporting, an agent has everything needed to decide and call correctly.

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 100%, so all four parameters, including the app identifier pattern and the timeout fallback semantics, are already documented in structured data. The description reinforces the wait semantics of timeout_minutes but adds no new per-parameter meaning such as acceptable alias formats or demo-data refusal details beyond the schema. 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?

The description names a specific verb and resource — 'Repair an installed Store or company application' — and immediately clarifies the mechanism: reinstall the installed version from the application repository without uninstalling, then wait. That distinguishes it from siblings like install_store_app, update_store_app, and validate_app_install without requiring the agent to open their schemas.

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?

It gives an explicit gating condition ('Only when the user asked for a repair') and enumerates cases where it is refused (app developed locally, inactive app, app containing plugins). What it lacks is a direct reference to a sibling alternative for those cases—e.g., pointing to update_app or install_store_app when the request is an upgrade rather than a repair.

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