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

Annotations already establish readOnlyHint, idempotentHint and closed-world behavior, so the safety profile is covered. The description adds genuinely non-obvious context: the call is metered, the price is 5 sats or US$0.005 USDC, data provenance is coinbase tags, and 'lightning' returns a BOLT11 invoice plus token rather than an x402 request. It does not cover failure modes on unpaid calls or whether results are cached per block, leaving a small gap.

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 with the payload description front-loaded and payment terms trailing, which matches how an agent decides whether to call. The only waste is the mild repetition in 'Paid per call. Price: ... per call.' Otherwise every clause carries 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?

With no output schema, the description takes on the job of describing returns and does so: per-pool block counts and share, plus the 10 latest blocks with pool attribution. Payment mechanics and price are also covered. What remains unstated is response shape specifics (ordering, units of share) and behavior when the invoice has not yet been paid.

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% for both optional parameters, so the baseline is 3. The description reinforces why l402 and pay_with exist by disclosing the per-call price and the two acceptance rails, but it adds no syntax or sequencing detail (for example, the order of invoice-then-token) beyond what the schema fields already state.

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 names a specific resource and scope: mining pools behind the last 144 Bitcoin blocks, derived from coinbase tags, returning per-pool block counts and share plus the 10 latest blocks. That is far more precise than the title alone. It does not explicitly name an alternative or sibling (e.g. bitcoin_latest_block, which also surfaces recent blocks), so it stops short of full differentiation.

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 scope 'last 144 blocks (about 24 hours)' implicitly tells the agent this is a rolling 24-hour pool-distribution view, which is a reasonable usage hint. However, there is no explicit when-to-use/when-not-to-use statement and no routing to competing tools such as bitcoin_latest_block or bitcoin_block_stats. The agent must infer fit from the scope alone.

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