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

Annotations already mark this as readOnly/openWorld/non-destructive, which is consistent with a tool that only builds an unsigned transaction. The description adds genuinely useful behavior beyond them: the server simulates for free, a bad signature costs no gas, and the returned tx must be sent from the same wallet that signed.

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 tight sentences, front-loaded with the mode constraint, then the how, then the safety/cost rationale. 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?

No output schema exists, and the description compensates by stating the return is one unsigned transaction to send from the same wallet. Prerequisites, cost behavior, and failure tolerance are covered; what to do afterward (which tool submits it) is not spelled out.

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 already 86%, so most fields are self-documenting. The description adds provenance meaning ('pass every field of `purchase` from geode_upgrade_prepare unchanged, plus your EIP-712 signature'), which tells the agent where each value originates and that the signature is the added input.

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 ('Build a one-transaction upgrade purchase') and scopes it to mode "authorization" only. It explicitly names the sibling it consumes from (geode_upgrade_prepare), letting an agent separate it from the other upgrade tools. The only mild opacity is what "mode" means without broader context.

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?

Gives an explicit gate ('For mode "authorization" only') and the prerequisite workflow (pass fields from geode_upgrade_prepare unchanged). It does not name when-not-to-use or contrast with geode_upgrade_status, but the staged dependency is clear.

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