idea_harvest

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

With no annotations, the description carries the full burden and does so richly: read-only, free, paced at ~0.3s/request, ~1.5 min for a full default sweep. It also discloses critical error semantics (failed feeds appear in failed_feeds with ok:False and must never be read as 'no apps') and that exclude_terms drops the founder's own apps by name/seller match.

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 passage is dense but front-loaded: the scope statement leads, then mechanics, then outputs, then operational caveats. Every clause carries signal, though the single long block is slightly heavy to parse relative to an ideal chunked structure.

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 complex 7-parameter tool the description covers scope, timing, failure behavior and output groupings; and since an output schema exists, return values need not be enumerated. The remaining gap is the un-described feeds/limit/max_results parameters and how they interact with the default sweep.

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 for all 7 params. It meaningfully explains genres (all 24 charted categories), countries (default us/gb/de/br/tr/jp/fr), newcomer_months (released ≤ N months) and exclude_terms, but leaves feeds, limit, and max_results entirely undocumented, so roughly half the surface remains opaque.

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 (idea harvest / Phase 0 sweep) and specifies the exact scope: top-grossing + top-free per genre × storefront. It even pre-empts a misreading by clarifying it is NOT limited to AI/photo apps, which distinguishes it from narrower siblings like aso_top_grossing.

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 'Phase 0' framing and the explicit 'across EVERY category... not only AI/photo apps' contrast give clear context for when this broad-harvest tool is appropriate versus narrower alternatives. However, no sibling tool is named explicitly (e.g. aso_top_grossing, aso_fetch_competitors, idea_evaluate), so the routing is inferred rather than stated.

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