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

The description goes well beyond annotations: it reveals non-custodial execution, that the returned transaction is unsigned and base64, that fees are charged past the free tier, and that re-trying with the same idempotency key replays the original result rather than re-uming an unknown current action. It also explains the Crank broadcast confirmation and balance-re-read behavior.

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?

The description is long but every sentence adds a meaning: purpose, units, mint selection, returning format, costing. It keeps repeated details compressed by saying 'see liquid_stake' instead of duplicating the two-phase protocol. The layout groups the optional key and the signed transaction phases into understandable chunks.

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?

Given a 9-parameter tool with an existing output schema, the description covers the main decision points and risks: route selection, base units, unsigned return step, idempotency replay, and two-phase broadcast. It delegates a part of the two-phase detail to liquid_stake and leaves one or two optional params unexplained, but those are optional and defaulted.

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?

With 0% schema description coverage, the description must carry the load. It does: amount is 'in base unit', lst_token is clearly one of mSOL/jitoSOL/bSOL, idempotency_key behavior is fully explained, and payment_header is tied to fee context. However, wallet_address (a required parameter) and pay_in_crank/caller_id are left to inference, so it is not fully complete.

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: 'Unstake an LST back to SOL'. It also clarifies non-custodial ownership and returns an unsigned transaction, so an agent can distinguish this from related staking, swapping, and bridge tools. This is more than minimally clear.

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 intended use is implicit but unmistakable: 'Unstake an LST' tells an agent when this tool is the right one. It also gives route-specific behavior and the two-phase execution flow, but it doesn't name alternatives or use when-not-to-use language. Clear context but no explicit exclusions.

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