proceeds

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

With no annotations, the description must carry the behavioral burden. It does disclose the data source, currency dimension, and comparison semantics, plus the 1-30 day constraint — meaningful context. It omits whether this is a read-only report, what permissions/reporting access are needed, data freshness/lag, and whether proceeds are gross or net of Apple's cut.

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 sentences, no filler, with the core comparison semantics front-loaded and parameter details following. The phrase 'the last `days` against the `days` before' is slightly compressed and requires a second read, but 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?

There is no output schema, so the description should sketch the return shape; 'by currency' hints at grouping but doesn't say whether results are per-currency totals, per-app breakdowns, or deltas/percentages. For a zero-annotation, zero-output-schema tool, that leaves an agent guessing about what it will actually receive.

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 0%, so the description must compensate, and it largely does: `app` is defined as a substring match on title, SKU, or Apple id with omit-for-all behavior, and `days` is bounded to 1-30. The only gap is that the default (7) is only visible in the schema and not reinforced, and the matching behavior for multi-app ambiguity isn't addressed.

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 metric (developer proceeds) from a specific source (App Store Connect Sales and Trends) with an explicit comparison window (last `days` vs. the `days` before). That distinguishes it from siblings like downloads, subscribers, and events, though the verb is implied rather than stated ('proceeds from...' rather than 'fetch/calculate proceeds').

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 explains the optional `app` filter ('leave it out for all apps') and the day range, which is useful usage context. But there is no guidance on when to pick this over `downloads` or `subscribers`, nor any prerequisites (App Store Connect credentials, data lag) that would tell an agent whether it can call it now.

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