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

Beyond annotations, the description discloses critical behavioral traits: the calldata is time-sensitive and must be signed and broadcast within 30 seconds, reverts should be retried at least once after rebuilding, Tenderly simulation may be unavailable, and the caller should verify the position exists via read_account_info before signing. These add substantial value beyond the readOnlyHint and idempotentHint annotations.

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 dense but each sentence earns its place: it defines the operation, explains a parameter nuance, warns about time sensitivity, gives a retry instruction, and advises a pre-sign verification. The most important framing, the atomic flash-action, is front-loaded.

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 complex transaction-building tool with five parameters, the description covers operation selection, address semantics, time sensitivity, failure handling, simulation limitations, and a pre-check prerequisite. Since an output schema exists, the description does not need to explain return values. This is complete enough for an agent to call the tool 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?

Although schema coverage is 100%, the description adds essential semantics that the schema omits: asset_address must be the non-staked PM address when staking and the staked PM address when unstaking. It also clarifies the action parameter as the operation selector and ties asset_id to the LP position NFT, making parameter selection materially clearer.

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 action-verb construction: 'stake, unstake, or claim rewards for an LP position in one atomic transaction.' This clearly identifies the resource (LP position) and the operations, and distinguishes it from sibling tools like write_account_add_liquidity or write_account_remove_liquidity.

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 gives clear operational context: use the action parameter to choose the operation, and choose the correct asset_address form depending on whether staking or unstaking. It does not explicitly name alternative tools or exclusion conditions, but the usage context is sufficiently clear for an agent to know when this tool applies.

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