App history (checkpoints)

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

Beyond the annotations (readOnlyHint, openWorldHint), the description discloses that the tool returns metadata only, not source, which is a deliberate design to keep context small. It also uncovers tombstone semantics (survives delete_app) and that each checkpoint snapshots both UI and manifest, providing restoration context.

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 three sentences, each adding distinct value: listing action, checkpoint numbering and restore usage, and tombstone persistence. No fluff, every sentence earns its place, and key details are front-loaded.

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 simple read-only list tool with a single parameter and an output schema, the description covers all necessary context: what it returns, what it doesn't return, how to use the results with restore_app, and edge-case behavior (deleted apps). No missing critical information.

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?

The schema only has a 'name' string with no description. The description's phrase 'an app's checkpoints' clearly implies 'name' is the app identifier, but it doesn't explicitly state that the parameter is the app name or define any format. Since schema coverage is 0%, the description provides just enough context but could be more explicit about the parameter's role.

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 states a specific verb ('List') and resource ('an app's checkpoints') with an explicit output shape ({checkpoint, ts, ui_size}). It clearly distinguishes itself from get_app by saying 'metadata only, NEVER the source' and from restore_app by noting that checkpoint numbers are used by restore_app.

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 explicitly tells when to use this tool: 'use get_app for the current source' for retrieving source, implying use app_history when you need checkpoint metadata. It also establishes a relationship with restore_app ('restore_app takes that number') and notes that history survives delete_app, which is useful for deleted apps.

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