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

Annotations declare readOnlyHint=true and openWorldHint=false, but the description describes an operation that pushes a transaction into a live P2P network, which is a side-effecting, open-world action. The description's own text ("Relay... to the network", "a rejected transaction is never relayed") contradicts the read-only and closed-world hints, so an agent trusting the annotations would badly misjudge the side effects. The rest of the behavioral detail (return shape, rejection semantics, RB_ENABLE_BROADCAST=1 gating) is genuinely strong, but the annotation conflict is disqualifying here.

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?

Every sentence carries distinct weight: purpose, when-to-use, when-not-to-use with alternatives, return contract, and deployment availability. The structure is front-loaded with labeled clauses ("When to use:", "Do not use:", "Returns:", "Availability:") and contains no filler.

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 tool with no output schema, the description covers the return shape, the failure shape, and a critical operational prerequisite (disabled unless RB_ENABLE_BROADCAST=1). The only shortfall is that it does not reconcile its network-facing behavior with the readOnly/closed-world hints it ships alongside.

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 50%: signed_raw_tx_hex is documented in-schema, while chain is only constrained by an enum (btc). The description adds meaningful semantics by stressing "already-signed" and "we never see a private key", clarifying that the payload must be signed elsewhere, but it adds no format or chain-selection 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?

The description opens with a specific verb and resource ("Relay an already-signed raw transaction to the network through our own full node") and immediately scopes it with the non-custodial constraint. It explicitly distinguishes itself from sibling readers like btc_get_transaction and ltc_get_transaction, so an agent can route correctly without opening another 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?

Usage is stated both positively ("an agent signed a transaction locally and wants a high-availability broadcast path") and negatively ("Do not use: to build or sign a transaction... or to look up a payment"), with the replacement tools named. This is explicit when/when-not/alternatives guidance.

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