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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: snapshots are cached for 24h, refresh=true forces recomputation, and the default returns summary + coverage while section=<engine> returns one engine in full. Missing only details like cost/latency of a refresh or what 'coverage' means.

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 long content enumeration is justified for a fact-base tool with many engines, and the description is front-loaded with purpose before contents and call mechanics. The single dense sentence for contents is hard to scan, and the usage instructions are buried at the end, which keeps it below a 5.

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 5-param, no-output-schema tool this is nearly complete: contents, default vs section behavior, cache/refresh semantics and required-connection fallback are all covered. The gaps are minor but real — window_days is never explained, and the description's fixed 'trailing 90 days' phrasing sits in tension with the window_days parameter and the prior-quarter/last-year comparisons it also claims.

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 60%, so the description must carry weight for some params and does: it clarifies section semantics (engine name 'in full' vs summary default), the default return shape, and refresh behavior. net_target_pct and seller_connection_id are already documented in the schema. window_days remains unexplained in both places (the description even fixes a trailing-90-day horizon without reconciling it with the 30–365 range).

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 concrete resource (the brand's quarter fact base) and enumerates its contents in detail, plus the key differentiator that it is 'computed by AMZ Vault from the warehouse (no report pulls needed)' — which implicitly separates it from siblings like pnl_by_asin, brand_sqp and the ppc_* report tools. The verb is only implied ('returns'), and no sibling is named explicitly, so it falls short of a 5.

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 says the facts are what 'a quarterly growth plan is written from', which hints at the growth_plan/growth_plan_upsert workflow, and it explains the default-vs-section call pattern. But there is no explicit when-to-use statement, no when-not, and no direct routing to the sibling tools (growth_plan, pnl_summary, brand_sqp) that an agent would otherwise reach for.

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