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

Goes well beyond the annotations: discloses latency ('expect a few seconds per call'), cache-warming semantics via words_fetched, non-fatal request problems surfaced in notes[], per-axis null delta semantics, and the warning that lost_phrases[] carries signal the score alone does not. Annotations (readOnlyHint=false, idempotent=false) are consistent with the saved-run behavior it describes.

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?

Front-loaded with the core action and the mode split, and nearly every sentence carries information (comparability warning, latency, cache effect). It is a single dense block, though, and the long return-value enumeration would scan better as separate sections.

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?

No output schema exists, so the description takes on the return contract itself and discharges it fully: app, aso_health axes and tier, delta null semantics, flags, lost_phrases with their caveat, the saved run, notes, and the words_probed/words_fetched meaning. Nothing an agent needs to call correctly or interpret results 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?

Schema coverage is 100%, so the schema carries the field documentation, but the description still adds real semantics: app_id inherits the live listing so { app_id, title } is complete, store/country/lang are only required without it, context keys merge over the app's real values, and kw_field is ignored on Google Play. It adds less about subtitle/description beyond what the schema says.

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 and resource ('Score a listing that does not exist yet') and immediately differentiates itself from the sibling audit engine and from check_metadata. The two-mode framing (with/without app_id) makes it unmistakable which tool this is.

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?

Explicitly says when to use it ('is my draft better than my listing'), the required parameters per mode, the prerequisite (check_metadata first, don't poll), and names the read-back alternatives (get_metadata_simulation, list_metadata_simulations). It also states when-not: without app_id the global score is not comparable and must not be presented as one.

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