Agent feature row (token-level, one call)

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

Annotations only declare read-only/non-destructive, but the description adds the critical behavior: a per-call cost of $0.03 USDC on Base, a split response with current_state recomputed in place vs observed on an immutable capture clock, and the lookahead-bias consequence of that split. These are operationally load-bearing facts 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 capability statement is front-loaded in the first sentence and the cost/scope/epistemic caveats follow in a sensible order. It is verbose and caps-heavy, and the parenthetical field lists are dense, but nearly every clause (payment, chain scope, current_state vs observed) carries decision-relevant 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?

No output schema exists, so the description must carry the return contract — and it does, enumerating payload sections and values. Combined with the cost, chain restriction, and data-freshness semantics, an agent has everything needed to call it correctly and interpret the result.

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?

Only one parameter, and the schema already documents it at 100% coverage with the exact address format (0x + 40 hex). The description adds nothing beyond 'Robinhood Chain token', so baseline 3 applies — the schema does all the work.

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?

Names a concrete verb+resource ('one call returns the token-level feature row') and enumerates the payload fields precisely, so an agent knows exactly what it gets. It also implicitly separates itself from prediction-style siblings by stating 'RobinX publishes INPUTS, not predictions,' but it never names an alternative like robinx_token or robinx_verdict, leaving the nearest-neighbor choice to inference.

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 clear usage context ('ready to fold into your own model', 'backtest them against your own forward returns') and a hard scope limit ('Robinhood Chain only'), plus a concrete misuse warning about joining current_state to a past timestamp. It stops short of explicitly saying when to pick this over robinx_token/robinx_verdict, so no exclusion routing.

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