withdraw_stakeAdvanced: Build an unsigned withdraw transaction for local signing. Most agents should use the withdraw tool instead, which handles signing and submission automatically.
| Name | Required | Description | Default |
|---|---|---|---|
| amountSol | No | Amount to withdraw in SOL (omit or null to withdraw full balance) | |
| walletAddress | Yes | Wallet address that is the withdraw authority | |
| stakeAccountAddress | Yes | Deactivated stake account to withdraw from |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool builds an unsigned transaction for local signing, which is a key behavioral trait not captured by annotations. It also signals it is an 'Advanced' operation. However, it does not detail potential side effects or prerequisites, but given the annotations already provide safety hints, this is sufficient.
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?
Two sentences, no fluff. The first sentence immediately states the purpose and mode, the second provides usage guidance. Every word earns its place, and the 'Advanced' prefix sets expectations upfront.
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?
The description is complete for a tool of this complexity (3 params, no output schema). It explains the tool's role in the withdrawal flow, differentiates it from the sibling tool, and notes the local signing use case. No further details are necessary to invoke or select it 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?
The input schema already provides full descriptions for all 3 parameters with 100% coverage. The description adds context that this is an unsigned transaction, which clarifies why parameters like 'amountSol' are part of the transaction-building process, but it does not go beyond the schema's parameter-level detail. Baseline 3 applies here.
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 clearly states 'Build an unsigned withdraw transaction for local signing,' specifying the exact action and output. It also distinguishes itself from the sibling 'withdraw' tool by noting that most agents should use that tool instead, making its unique purpose unambiguous.
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?
Explicit guidance is provided: 'Most agents should use the `withdraw` tool instead, which handles signing and submission automatically.' This directly tells the agent when to choose this tool over an alternative, making the usage context very clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have distinct purposes, but there is some overlap between the 'stake' and 'create_stake_transaction' tools, as well as between 'unstake' and 'create_unstake_transaction', and 'withdraw' and 'withdraw_stake', which could cause confusion. However, descriptions clearly differentiate between automated and advanced manual use cases, mitigating ambiguity.
Tool names follow a consistent verb_noun pattern throughout, with clear and descriptive naming (e.g., check_balance, get_staking_summary, register_webhook). There are no deviations in style or convention, making the set highly predictable and readable.
With 26 tools, the count is borderline high for the staking domain, potentially overwhelming for agents. While many tools provide specialized functionality, some could be consolidated (e.g., multiple transaction-building tools), making the set feel slightly heavy but still within a reasonable scope.
The toolset comprehensively covers the staking lifecycle, including address checking, balance queries, staking, unstaking, withdrawing, monitoring, simulation, and verification. There are no obvious gaps, and tools provide clear guidance and alternatives, ensuring agents can handle all necessary operations without dead ends.