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

With annotations present (openWorldHint, idempotentHint, readOnlyHint=false), the description still adds real value: it discloses the exact fee (0.005000 test USDC on eip155:84532) and instructs the agent to preserve idempotencyKey for retries, which is more concrete than the idempotentHint flag alone. The only friction is the "Read" wording against readOnlyHint=false, but that is explained by the paid-call side effect rather than being a true conflict.

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 sentences, each carrying distinct information (method, chain, price, retry hygiene), with no filler. The long chain id is verbose but unavoidable for disambiguation.

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 paid tool with no output schema and a cryptographically patterned positional params array (txid, verbose=false, optional blockhash) that the schema doesn't describe, the description should have covered what params must contain and what is returned. It leaves the agent guessing about the core input and the raw-hex output.

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%, and the undocumented parameter (the 3-item positional params array) is not clarified at all in the description. The only parameter the description touches, idempotencyKey, is already fully documented in the schema, so the description adds essentially no parameter semantics of its own.

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 getrawtransaction from Bitcoin" does state a verb and a resource, and the chain identifier pins down which network it targets. However, the resource is literally the upstream RPC method name restated from the tool name, and it never explains that the result is a raw serialized transaction (nor how it differs from siblings like bitcoin_gettxout). Purpose is decipherable but not enriched.

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 statement of when to use this tool versus the many sibling transaction/block lookups, and no prerequisites beyond the retry note. The cost line implies a paid call but doesn't tell the agent under what circumstances to prefer this over other Bitcoin reads.

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