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

Beyond readOnlyHint/openWorldHint, it discloses the data provenance (two upstream sources), a coverage limitation (~10 newest unconfirmed txs only), the semantics of the value field ("includes change", so output value is not net transfer value), the `scanned` provenance field, and billing behavior ($0.005 per successful call via x402; failed calls free). It also flags partial-block semantics by saying `scanned` states exactly what was read.

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?

Front-loaded with the threshold and scope, then sources, return fields, provenance, alternatives and price in a logical order with no filler. The sibling-routing sentence is awkwardly worded ("for a different need: X when you need Y") and slightly bloats the definition, but nothing is redundant enough to cut outright.

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 two-parameter, open-world read tool with an output schema and annotations, this covers everything an agent needs: what is scanned, from where, what fields come back, what `scanned` means, when to pick a sibling, and that the call costs money. Recency/freshness caveats are the only thing not addressed.

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 the baseline is 3; the description slightly exceeds it by clarifying that minBtc is measured against total output value including change, which affects how an agent should set the threshold. The 1-2 block range and 10 BTC default merely restate 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?

"Large Bitcoin transactions (total output >= minBtc, default 10 BTC)" names the resource, the filtering rule and the threshold, then lists the exact sources (mempool.space block summaries, blockchain.info unconfirmed). It also names the sibling tools it is not (crypto_btc_block, crypto_btc_node_diversity), so an agent can discriminate it without opening a schema.

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?

It routes explicitly to alternatives: "crypto_btc_node_diversity when you need Reachable Bitcoin nodes" and "crypto_btc_block when you need Detailed Bitcoin block summary." What is missing is a direct statement of when to choose this tool (e.g., whale/large-transfer monitoring) and any exclusion such as "not for full block contents."

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