App history (checkpoints)

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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds genuinely non-obvious behavior: history survives delete_app (tombstone), checkpoint 1 is oldest, and each checkpoint snapshots all slots (ui, manifest, skill) restored together. These are behavioral facts an agent could not derive from 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?

Four dense sentences, front-loaded with the core action and response shape. Every clause carries weight (shape, metadata-only, ordering, tombstone, snapshot semantics), though the em-dash parentheticals make it slightly cramped. Nothing is wasted.

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?

Output schema exists so return fields needn't be explained, yet the description still supplies the checkpoint-ordering semantics needed to call restore_app correctly. Safety profile is covered by annotations and the metadata-vs-source distinction is fully stated. Nothing required for correct invocation is missing.

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?

Only one parameter ('name') exists and schema coverage is 0%, so the description should compensate, but it only implies name via 'an app's checkpoints'. The rich detail it provides is about return-field semantics (checkpoint numbering), not the input parameter. Adequate but not a full 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?

States a specific verb+resource ('List an app's checkpoints') and even declares the response shape ({checkpoint, ts, ui_size}). It distinguishes itself from the sibling get_app by framing this as metadata-only versus current source. An agent can tell exactly what this returns without opening the schema.

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?

Names the alternative tool and the condition that selects it ('metadata only, NEVER the source ... use get_app for the current source'). It also routes to restore_app by explaining which checkpoint number that sibling consumes. This is explicit cross-tool routing, not inference.

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