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

Annotations already convey mutation, non-idempotency, and destructive potential, so the description only needs to add behavioral nuance. It adds a key fact beyond annotations: the tool does not sign locally and only broadcasts a pre-signed payload, meaning signing responsibility rests entirely with the caller. It also names the target network (Arbitrum), consistent with the openWorldHint; no contradiction exists.

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 earning its place: the core action is stated first, the prerequisite second, and the negative clarification last. The 'does NOT sign' sentence is not redundant because it prevents the common mistake of expecting the tool to handle signing.

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 one-parameter tool with annotations and an output schema, the description is complete: it explains what the tool does, the required prior step, the target network, and the non-signing boundary. There is no missing information an agent needs to invoke it correctly.

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?

The input schema already documents signedRawTransaction thoroughly with hex format and examples, so the baseline is 3. The description adds a critical semantic constraint not present in the schema: the transaction must come from prepare_gmx_order output and must have been signed by the caller. This meaningfully clarifies what value to pass.

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 uses specific verbs 'Relay/broadcast' and a specific resource: a signed Ethereum transaction to the Arbitrum network. It clearly distinguishes the tool from signing-related siblings by stating it only broadcasts an already-signed transaction. The prerequisite link to prepare_gmx_order output removes ambiguity about what this tool is for.

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 description explicitly states the transaction must have been pre-signed by the caller using prepare_gmx_order output, creating a clear before-condition. It also tells agents when not to use this tool: 'This endpoint does NOT sign.' This leaves little to inference about the boundary between submit_gmx_order and prepare_gmx_order.

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