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

Annotations already mark this as a destructive, non-idempotent, open-world write, but the description adds substantial behavior beyond that: HMAC permit re-verification, on-chain state re-read, re-simulation before broadcast, an enumerated set of failure modes (permit mismatch, state change, expiry, simulation failure), and the success return value. This is exactly the pre-call risk context an agent needs before broadcasting.

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?

Four tight sentences: action, execution sequence, failure modes, return value. The sequencing constraint is front-loaded and no sentence is 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 13-parameter destructive write with no output schema, the description covers execution flow, sourcing of arguments, failure conditions, and the success return. It stops short of addressing retry safety after a failed simulation or what a partial-broadcast state would look like, which matters for a non-idempotent tool.

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 85%, so most parameters are already documented, but the description adds the crucial constraint that all submitArgs fields must be echoed unchanged from the prepare_transaction response rather than constructed by the agent. It does not explain the optional unsignedTransaction path beyond what the schema already says.

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?

States a specific verb and resource ('Submit a signed add-liquidity transaction') and immediately ties it to the prepare_transaction step, which separates it from siblings like submit_open_position and submit_compound_transaction that handle different transaction types. An agent can identify the correct tool without opening the 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?

Explicitly tells the agent to pass signedTransaction plus every field of submitArgs from the prepare_transaction response, unchanged — a clear prerequisite and ordering rule. It does not explicitly state when not to use it (e.g. for open/withdraw/compound flows), relying on the name for that exclusion.

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