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

Annotations already declare readOnly, idempotent, and closed-world, so the safety profile is covered; the description adds materially different context: the node is pruned to ~10,000 recent blocks and each call is paid (3 sats / US$0.003), which an agent must know before invoking. It stops short of describing the payment handshake flow itself, which is left to the schema's l402/pay_with fields.

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?

Two sentences, front-loaded with the resource and capped by pricing. The metric enumeration is long but each item is informative; the pricing sentence is required for a paid endpoint and is not padding.

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 one-required-param read tool with no output schema, the definition covers what is returned (by metric name) and the two non-obvious operational facts: pruned history depth and per-call cost. The only gap is that it does not explain the x402-vs-Lightning payment path or what happens on an unpaid call, which the agent must derive from the parameter descriptions.

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 100%, so block_id (height or 64-hex hash), l402, and pay_with are already documented at the parameter level. The description only reiterates the height-or-hash choice and adds the pruning window as an implicit bound on valid heights; it offers no extra syntax or format detail beyond the schema.

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?

States a specific resource and scope ('Statistics for one recent Bitcoin block... by height or hash') and then enumerates the exact metrics returned: tx count, total fees, fee-rate percentiles, size, weight, subsidy, inputs/outputs, SegWit share, and miner/coinbase tag. The metric list cleanly separates it from neighbors such as bitcoin_block_header, bitcoin_latest_block, and bitcoin_mempool_blocks without needing to name them.

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 context is implied rather than stated: the caller learns it takes a height or hash and that the node only retains roughly the last 10,000 blocks, which constrains which blocks are valid targets. It never says when to pick this over bitcoin_block_header (header-only) or bitcoin_latest_block, so the agent must infer the choice from the metric list.

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