One app's featuring history and impact

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

Annotations only cover readOnlyHint/openWorldHint, and the description adds genuinely non-obvious behavior: *_series arrays are undated with index 0 as start_date and one element per day, set series to rezip dates, and invalid filters return 200 with empty arrays instead of 422. The last point is exactly the kind of silent-failure quirk an agent cannot get from structured fields.

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?

Three sentences, no filler, and the highest-value fact (the undated *_series arrays and the series=true fix) is embedded inline with the mode description rather than buried. Every clause carries a distinct operational fact.

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?

With no output schema, the description does explain return shape per mode (position + download attribution for creatives; aggregated occurrences/downloads for impacts) and flags the empty-array ambiguity. For a 14-parameter tool it leaves pagination and the behavior of undocumented filters like types/countries unaddressed, so it is strong but not exhaustive.

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 57%, so the schema documents some parameters (os, limit, fields, format, dry_run, series, nonzero, breakdown) while leaving types, countries, start_date, and end_date bare. The description compensates by explaining the semantics of mode, series, and the country/type breakdown, but not the undocumented date/country/type filters.

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 names a concrete resource (one app's featuring history) and splits it into two well-defined modes: creatives (every featuring with position and download attribution) versus impacts (aggregated occurrences and downloads by country or type). That is a specific verb+resource statement. It does not explicitly contrast itself with the sibling sensortower_featured (non-history), so it stops short of full sibling differentiation.

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 clearly routes between the two modes and gives the condition for series=true ('its *_series arrays carry NO dates... so set series=true to have them zipped back onto real dates'). It also warns that invalid filters yield a 200 with empty arrays, which is actionable usage context. No explicit 'do not use this when...' versus sibling tools is given.

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