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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is known. The description adds substantial behavioral detail beyond annotations: it lists the exact fields returned, explains null creator for private profiles, describes group_by behavior, and clarifies that filters only apply in link mode. This is rich, non-contradictory context that goes well beyond the structured 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 description is long but every sentence carries essential information. It is front-loaded with the core purpose and then details the output fields, usage, and filters. There is no fluff or repetition; each clause adds value. The structure is logical: purpose → fields → usage → grouping → filters.

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 read-only list tool with no output schema, the description is exceptionally complete. It covers the return fields, edge cases (private creators), grouping modes, filter constraints, and how to act on the results. An agent can correctly invoke the tool and interpret the output without additional information.

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 75% (3 of 4 params have descriptions). The description adds meaning beyond the schema: it explains the group_by enum values and that brand and creator_uuid filters are link-mode only, which is not in the schema. It also clarifies the default group_by behavior. The page parameter is not described in the schema, but the description doesn't add anything about it either, so there's a minor gap. Overall, the description compensates well for the schema's limitations.

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 clearly states the tool lists click history for links the account has clicked as a shopper, newest first. It specifies the exact resource (click history) and the action (list). It distinguishes itself from siblings by explaining the purpose of finding previously seen items to buy and credit the creator, which is unique among the many split_* tools.

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?

The description provides strong usage context: it's for finding something seen earlier via a creator's link and buying it so the creator is credited. It explains how to use the output (open shop_it_url or pass to split_click_link). However, it does not explicitly name alternatives or state when not to use this tool, though the purpose is clear enough that an agent can infer typical use cases.

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