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

Annotations already establish readOnlyHint=true and openWorldHint=false, and the description adds the critical non-annotation trait: this is a paid call at $0.05 USDC. It does not cover result size, latency, or failure behavior for an unset selector, but the pricing disclosure is the highest-value behavioral fact for this tool.

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 compact sentences with the cost front-loaded and the metric list following immediately. Dense but well ordered, with no filler; the only cost is that the metric run-on trades readability for brevity.

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 correctly enumerates the returned fields, which is the main gap it must fill. For a 4-parameter read-only snapshot tool, the remaining omissions — selector precedence and response shape/size — are minor rather than blocking.

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 50% — api_key and category are documented in-schema, while brand and domain have no descriptions. The description compensates partially by framing domain/brand/category as alternative selector inputs, but it never clarifies whether they are mutually exclusive, combinable, or what the default universe is when all are omitted.

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 concrete verb+resource: a precomputed snapshot for a store domain, brand, or category, enumerating exactly which metrics come back (product/variant counts, in-stock %, price stats, discount depth, 7-day change counts). It does not name or contrast with nearby siblings such as ecom_product, ecom_changes, or ecom_catalog, so an agent must infer the boundary itself.

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?

Usage is only implied: use this when you want an aggregate rollup rather than a single product lookup, and pass a domain/brand/category. There is no explicit when-not guidance, no mention of the free_ecom alternative, and no statement about what happens when no selector is supplied despite required=[].

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