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

With no annotations, the description carries the full burden and does substantial work: it discloses the result cap (10 per call), the sort order (most-visited first), the returned fields (apps, spend estimate, gaps, public contacts), the index population, and a per-call price of $0.01 via x402/USDC — an unusual and important cost signal. Deduction for referencing "page with offset" when no offset parameter exists in the schema, which muddies the pagination story rather than clarifying it.

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 dense sentences that front-load the core capability before filters, result shape, and price — a sensible order with little filler. The price/payment clause and the pagination clause are both load-bearing, though the offset reference costs clarity rather than saving space.

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 6-parameter, annotation-free, output-schema-free search tool, the description does well on return shape, ordering, cap, and pricing. It is still incomplete on the questions that decide correctness: what separates `missing` from `exclude_app`, whether `app` and `q` are exact matches or fuzzy, and how to page when no offset field exists.

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 description coverage is 0%, so all six parameters depend on the prose, and the prose never maps to parameter names. Worse, the two closest-looking filters — `missing` and `exclude_app` — are never differentiated despite both appearing to mean "without an app," leaving the agent to guess. The description also describes paging via offset, a parameter that is not in the schema, which actively misleads.

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 opens with a specific verb and resource: "Find Shopify stores by the apps they run or lack," then enumerates concrete filter axes (app, missing app, country, niche keyword, spend). This is far more than a restatement of the name. It stops short of a 5 because the singular sibling shopify_store is never named or contrasted, so the agent must infer the split between store search and single-store lookup.

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?

Concrete example queries ("stores using Klaviyo, stores without a loyalty app") give the agent a clear sense of when this tool fits, and "From our index of high-traffic Shopify stores" bounds the population being searched. There are no explicit exclusions or pointers to alternatives when the query is about a known domain rather than a segment.

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