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

The annotations already indicate readOnlyHint, idempotentHint, and non-destructive, so the description doesn't need to restate those. It goes beyond by explaining the behavior of omitting records for factory/relayer wallets and single-launch wallets, which is non-obvious and critical for interpreting results. It also clarifies that no win rate is computed because 'crossed' rows only exist for successes, preventing the agent from inferring a misleading statistical field. This is a deep behavioral disclosure that annotations do not cover.

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 a single well-structured paragraph that starts with the core value proposition, then explains the filtering logic, and ends with the win-rate rationale. It is front-loaded with the key question an agent would ask ('What one wallet has launched...'). Every sentence earns its place, though the latter half gets into nuanced details that might be dense for some agents. It is not overly long but is dense with information.

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?

Given the tool has a single parameter, a simple input schema, and no output schema, the description is more than complete. It tells the agent what to expect (tokens, liveness, liquidity, crossings), what to not expect (no record for certain wallets, no win rate), and the rationale behind those behaviors. There is nothing an agent needs to call this tool correctly that is missing. The complexity is low, and the description addresses all potential questions.

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?

The schema has only one parameter, address, with no description coverage. The description doesn't explicitly explain the format or validation of the address, but it implies it's a wallet identifier. Since the parameter is self-explanatory (an address string), the description doesn't need to add much. However, it could have clarified that the address is expected to be a Robinhood Chain wallet, but that is implied by the tool name. Baseline 3 is appropriate because the schema is minimal and the description adds limited but sufficient context.

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 purpose: to show what one wallet has launched on Robinhood Chain and how those launches went, focusing on tokens, liveness, liquidity, and crossing $100,000. It distinguishes this tool from siblings like rh_wallet_record and rh_chain_stats by emphasizing the deployer's perspective. The description uses specific terms like 'launchpad rows' and 'crossed $100,000' to make the functionality unmistakable.

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 explicitly explains when to use this tool: when a launchpad buyer wants to know if a wallet has launched tokens successfully. It also states when not to use it, by detailing the exclusion of factory/relayer wallets and single-launch wallets. It references 'wallet above the launch ceiling' and 'one launch is a fact about a token', giving clear criteria for when no record is returned. This guidance is comprehensive and prevents misuse.

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