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

Annotations cover safety/idempotency (destructive=false, idempotent=true, openWorld=true), and the description adds genuinely useful context beyond them: a concrete cost (0.002500 USDC on Base mainnet) and the instruction to preserve idempotencyKey across retries. The readOnlyHint=false is explained by the paid nature of the call. It stops short of describing the return payload, but no output schema exists so this is a moderate 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?

Three short, front-loaded sentences with no filler; the cost and idempotency notes each carry actionable information. The opening clause is the weakest since it largely echoes the name, but the rest is tight.

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 tool with no output schema and an undocumented `params` array, the description should explain what the array elements mean and ideally what a block header contains. It covers payment and retry semantics well but leaves the core input shape unexplained, which is a meaningful gap.

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 only 50%: idempotencyKey is fully described, but the `params` array (a 64-char hex hash plus a boolean) has no item-level descriptions. The description text says nothing about the array's structure or what the boolean controls (verbosity), so it fails to compensate for the coverage gap.

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?

"Read getblockheader from Bitcoin" essentially restates the tool name rather than defining what a block header is or what the tool returns. It identifies the chain (via CAIP id) but does not distinguish it from siblings like bitcoin_getblock, bitcoin_getblockhash, or bitcoin_getbestblockhash.

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?

There is no guidance on when to use this tool over bitcoin_getblock (full block) or bitcoin_getblockhash (hash only). The only usage hint is the retry note tied to idempotencyKey, which is about re-invocation, not tool selection.

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