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

Annotations already carry readOnlyHint=true and destructiveHint=false, so the safety profile is covered and there is no contradiction. The description adds genuine context beyond the annotations: the premium/paywalled nature, the prepaid-credit pricing model, the signing dependency on orbitpay_info, and the alternative x402 HTTP route. That disclosed auth/payment behavior is valuable. But it omits details like pagination limits affecting cost and what happens on failed payment.

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 text is short with no filler and front-loads the primary purpose before payment details. However, it allocates roughly two-thirds of its scarce space to payment mechanics (USDT pricing, orbitpay_info signing, x402 route/URL) at the expense of tool semantics and parameters. It is compact but mis-prioritized for an agent that needs to know what the tool returns and how to call it.

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 premium, pay-per-row data tool with no output schema and no parameter descriptions, the description is materially incomplete. The agent knows the cost model but not what supply data is included, how the five parameters shape the query, what the response looks like, or what filters are available — all of which matter when the agent is paying real money per 100 rows. The payment focus leaves the core call semantics undocumented.

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 0% with 5 parameters (to, from, limit, cursor, filters), and the description explains none of them. There is no mention that to/from bound a date range, that limit is capped at 200, that cursor drives pagination, or — critically — what keys the nested 'filters' object accepts. The only oblique hint is 'per 100 rows', which gestures at limit/cost coupling. With zero schema coverage, the description was obligated to compensate and did not.

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 states the resource ('token supply data') and flags it as premium/archival, giving a recognizable purpose. However, it is a noun phrase with no verb, and 'supply data' is vague — it never says whether this is current supply, historical series, per-token, or aggregate. It also fails to distinguish itself from several overlapping siblings (orbitpay_economics_series, get_token, list_tokens), so an agent cannot reliably tell this tool apart without opening schemas.

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 gives payment-process guidance — it instructs prepaid-credit agents to 'call orbitpay_info' for signing and offers a wallet-holders alternative via an x402 HTTP route. This is useful operational guidance, but it is payment guidance, not tool-selection guidance. There is no statement of when to choose this tool versus orbitpay_economics_series, orbitpay_tags_export, or get_token, and no exclusion criteria. With six orbitpay_* siblings, that absence is a real gap.

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