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

Beyond the readOnly/idempotent annotations it discloses OAuth store:read consent, the requirement of an owned approved store, what is returned (including that no approval tokens come back), what fails (invalid selections/cursors, unowned integrations), and what is skipped (unsuitable guidance, checkout holds, sale-priced copies). It also warns that catalog asks are not live or grade-matched sold comps and that this does not configure recurring repricing — real behavioral context an agent cannot infer from annotations.

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 critical scoping and sibling routing is front-loaded, but the paragraph is dense and mixes purpose, prerequisites, return values, skip behavior and error cases into long run-on sentences. Some content is redundant — 'Read-only; no prices, strategy, enrollment or export jobs change' repeats both the readOnlyHint annotation and the earlier 'This read does not grant write approval'.

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 six-parameter preview tool with no output schema, the description covers prerequisites (OAuth consent, approved owned store), return contents (current/market/proposed prices, timestamps, cached ask, skipped reasons, nextCursor, review URL) and failure modes. Nothing an agent needs to call it correctly appears to be 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 description coverage is 100% and the schema already explains cursor pagination, cardType enum, strategy omission, direction filtering with ongoing repricing, integrationId and automationMode. The description's only extra gloss is 'An omitted strategy uses the store setting', which largely restates the schema, so it adds little meaning beyond structured fields.

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 ('Preview one-time price changes') with the scope ('RAW, graded or all cards') and explicitly contrasts itself with supercatch_prepare_card_price_updates for exact prices/approvals. An agent can separate this read-only preview from the sibling prepare/execute tools without opening a schema.

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?

Gives concrete when-to-use triggers ('researching current, market and cached lowest asking prices', 'comparing strategy proposals before website approval') and names the alternative for exact custom prices or in-chat approvals. However, it does not clarify how this differs from other pricing read siblings such as supercatch_get_price_plan, supercatch_get_pricing_context or supercatch_preview_auto_repricing, so the routing is only partly resolved.

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