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

The non-execution disclosure ('Construct unsigned transactions ... Does NOT execute — the user must sign') adds real value beyond the annotations, telling the agent the call produces unsigned payloads and that user signing is a required downstream step. This is consistent with destructiveHint=false and readOnlyHint=false. It does not cover what the constructed payload looks like or what happens with a stale passthrough, but the output schema carries the return shape.

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, front-loaded sentences with zero waste: purpose first, then the critical non-execution caveat, then the sourcing constraint. Nothing is padded.

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?

With a full output schema, annotations, and 100% parameter coverage, the description supplies the two things structured fields cannot: the unsigned-transaction semantics and the mandatory upstream source for action/passthrough. The only gap is the sibling boundary against actions_enter/actions_exit.

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 description coverage is 100%, so the baseline is 3; the schema already documents yieldId, address, amount, action, passthrough and executionMode sources and defaults. The description's sourcing instruction for action/passthrough restates what the schema fields already say, adding no new semantics.

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 ('Construct unsigned transactions for a pending action') and gives concrete examples (claiming rewards, restaking, unlocking funds). It does not, however, explicitly differentiate itself from actions_enter or actions_exit, which overlap with the STAKE/UNSTAKE values in its own action enum.

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 a strong, explicit precondition: the action type and passthrough must come from yields_get_balances balances[].pendingActions[] and must not be guessed. That is excellent context, but there is no guidance on when to prefer this over actions_enter/actions_exit for the overlapping action types.

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