listing__diff_metadata

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

Annotations already declare readOnlyHint=true, and the description reinforces that with 'Read-only.' More importantly, it discloses behavior beyond the annotation: the one-call locale-by-locale comparison, the default version selection, the specific list of fields compared (description, keywords, whatsNew, promotional text, marketing URL, support URL), and the reporting of added/dropped locales. This gives an agent a clear picture of what the operation is doing.

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 and front-loaded: it leads with the core purpose, then gives the necessary app-identification instruction, then explains default behavior, and finally the exact output scope. Every sentence earns its place; the 'what am I about to change?' framing adds practical orientation without bloat.

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?

The description covers the tool's purpose, default comparison versions, required app identifier, per-locale reporting, and the exact set of fields checked. With a rich output schema already present and a read-only annotation, nothing essential is missing for an agent to select and invoke this tool 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 coverage is 100%, so the baseline is 3, but the description adds meaningful value by specifying that 'app' can be a name, bundle ID, or Apple ID—details not present in the schema. It also reinforces the default from/to behavior, which aligns with and supplements the parameter descriptions.

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 uses a specific verb ('Compare the store text of two app versions') and clearly delimits the result ('list only what differs'). It names the exact resource (store text of two app versions, locale by locale) and distinguishes itself from siblings like listing__get_screenshots or metadata_ai__audit_localizations by focusing on a diff of metadata fields.

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 gives strong contextual guidance: it explains the default comparison between the version on sale and the version being prepared, framing it as 'what am I about to change?'. It does not explicitly name alternatives or exclusion criteria, but the use case is clear enough that an agent can decide when to invoke it.

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