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

Annotations already declare read-only, idempotent and closed-world, so the description's added value is the commercial behavior: every call is billed at 5 sats / US$0.005 USDC, and the lightning path returns a BOLT11 invoice plus token that must be replayed as '<token>:<preimage>'. That is material context an agent cannot get from the annotations. No rate limits or failure/expiry behavior for the payment token is described.

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?

Content is front-loaded: what data comes back first, then the payment mechanics. It is dense but wastes little; the parenthetical source and the price sentence both earn their place. Slightly long sentences reduce scannability.

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?

There is no output schema, yet the description enumerates the per-block fields plus the aggregate averages and trend, so an agent knows what comes back. Combined with full schema coverage and annotations covering safety, the only gap is response envelope/pagination, which is minor for a fixed 12-block payload.

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 100% and both optional parameters (l402, pay_with) are documented in the schema, including the enum. The description adds nothing about parameter semantics beyond the general per-call pricing statement, so the baseline 3 applies.

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?

"Fee rates actually paid in the last 12 Bitcoin blocks" names a specific verb-like scope (paid fees), the exact resource (last 12 blocks) and enumerates the returned fields (10th–90th percentile sat/vB, total fees, tx count, fullness, time, averages, trend), with the data source (getblockstats) named. The word "actually paid" implicitly separates it from bitcoin_fee_estimates, but no sibling is named explicitly.

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?

Usage is only implied: an agent can infer this is for historical/realized fee context rather than forward-looking estimates. There is no explicit statement of when to prefer this over bitcoin_fee_estimates, bitcoin_block_stats or bitcoin_latest_block, and no exclusions or prerequisites beyond the payment note.

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