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

Annotations already flag destructiveHint=true, idempotentHint=false and readOnlyHint=false, but the description goes well beyond them: OAuth scope store:prices:write, the requirement to own an approved store, exactly what state is mutated (approved listing prices plus pricing history, cache, notifications, marketplace-sync state) and what is explicitly not touched (stock, order, automation settings). It also discloses non-atomic behavior ('a batch can partially succeed') and stale-token refusal, which annotations cannot express.

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 constraint (apply only explicitly confirmed prices) is front-loaded and each sentence carries distinct information: precondition, exclusions, return shape, auth, side effects, refusal cases, retry rule. It is dense for a destructive write tool but not padded; the trailing retry sentence could arguably be folded into the uncertainty sentence rather than standing alone.

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 compensates by describing return values (per-listing applied, skipped or uncertain outcomes and their totals) and partial-success semantics. Combined with auth requirements, ownership precondition, mutation scope, non-atomicity and retry guidance, an agent has everything needed to call this destructive operation correctly.

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 100%, so both parameters are already documented and a 3 is the floor. The description adds genuine provenance meaning the schema does not: tokens originate from a reviewed preparation, they are per-exact-price, they can be expired or invalidated by changed proposals, and 'confirmed' must be true before calling. It stops short of explaining token payload or batch limits, but the added semantics are real.

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 ('Apply ... exact card prices explicitly confirmed by the user') and immediately scopes it against adjacent operations: the reviewed preparation that issues tokens, fresh recommendations, ongoing repricing and publishing. An agent can distinguish this from supercatch_prepare_card_price_updates, supercatch_execute_price_changes and supercatch_preview_auto_repricing without opening any 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 an explicit precondition ('Use after a reviewed preparation returns signed tokens ... confirmed must be true'), explicit exclusions ('Fresh recommendations, ongoing repricing and publishing are outside this operation') and explicit failure handling ('Uncertain outcomes require checking current prices before retrying'). It also names the refusal cases (unconfirmed, expired or changed proposals), so when-not-to-call is covered as well as when-to-call.

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