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

Annotations already declare readOnly/idempotent/closed-world, and the description usefully adds beyond them: "Nothing here holds a key", prices are eth_calls via wire rather than card numbers, 'earned: null' means the check failed, and 'live' returns null when unknown. The only ambiguity is 'prepare' (`fields` to save) under readOnlyHint, but the phrase "dry run" keeps it from being a direct contradiction.

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?

Nearly all content is load-bearing mode definitions, but it is delivered as one dense run-on paragraph with inconsistent line breaks, so it is hard to scan for the mode an agent needs. A short leading sentence plus a structured mode list would cost no extra words and be far more usable.

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-parameter multiplexer with no output schema, the description explains modes and parameter roles but says nothing about what any mode returns (e.g. shelf listing shape, ticket/wallet copy, leaderboard rows). Safety and pricing context are well covered, yet an agent still has to call blind on response structure.

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% and all five parameters have bare titles/defaults, so the description carries the full burden — and it does: it defines the `what` mode vocabulary and its default 'shelf', and assigns meaning to `slug`, `wallet` ("the text to sign" for entitle, "narrows" for items), `signature`, and `fields`. The mapping is terse and mode-scoped, but every parameter gets semantics that the schema does not supply.

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 only "The store." and never states a verb or the overall purpose; the intent emerges indirectly from a long enumeration of `what` modes (shelf, title, ticket, buy, entitle, items, reviews, achievements, log, desk, prepare, live, leaderboard). An agent can infer this is a mode-dispatched storefront/game-marketplace reader, but there is no single sentence naming the resource and action, and no explicit contrast with siblings like `exchange`, `trade`, or `collections`.

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 implied per mode rather than stated: 'buy' explains that the tool returns unsigned calldata and your wallet signs and sends, 'prepare' is called "a keeper's dry run", and 'entitle' with `signature` yields the download grant. That gives real situational cues, but there is no when-not guidance, no prerequisites, and no routing to alternatives among the many sibling tools.

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