Build a NON-CUSTODIAL Solana swap transaction (via Jupiter) with a 0.20% service fee embedded + a Guard safety check on the output mint. Returns an UNSIGNED transaction; the agent signs and sends with its own wallet. We never hold keys or funds.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | input amount in smallest units (lamports for SOL) | |
| input_mint | Yes | ||
| output_mint | Yes | ||
| user_pubkey | Yes | the agent's own wallet pubkey (signer) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden, and it does so well: non-custodial, embedded fee, Guard safety check, unsigned transaction, and no custody of keys/funds. It stops short of explaining Guard failure behavior or transaction-level details, but covers the most important behavioral traits.
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 dense sentences with no filler; the most important safety and custody facts are front-loaded before execution instructions. Every clause adds value.
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 four-parameter tool with no output schema, the description explains the return value (unsigned transaction) and the follow-up action (agent signs and sends). It could specify Guard failure handling and whether slippage is configurable, but the core invocation context is present.
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 50%; amount and user_pubkey already have schema descriptions. The description adds context for output_mint via the Guard check and reinforces user_pubkey as the signer, but does not clarify input_mint/output_mint address format or placeholder details, leaving a moderate gap.
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 ('Build') and resource ('Solana swap transaction via Jupiter'), and adds scope-defining modifiers: non-custodial, 0.20% fee, Guard check on output mint, unsigned. This clearly differentiates it from the sibling list, none of which is a swap transaction builder.
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?
Usage is implied: use this when the agent needs to construct a swap transaction that it will sign itself. However, the description never states when not to use it or points to sibling alternatives such as check_mint or guard_pricing for pre-swap safety checks.
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 target distinct actions (build a swap, check a mint, verify a claim, fetch pricing), and the descriptions make boundaries clear. The main risk is mild confusion between check_mint/score_mint and copy_signals/recent_events, as both pairs sit in adjacent signal/safety territory, but they are not interchangeable.
Most names follow a verb_noun pattern (build_swap, check_mint, score_mint, verify_claim, track_record). guard_pricing and recent_events break that pattern slightly, but the naming remains predictable and readable overall.
Nine tools is well within the ideal range and each tool earns a place in the safety/signal/trading workflow. It is neither bloated with near-duplicates nor too thin to define a useful server.
The server covers a coherent lifecycle: discovery (recent_events/copy_signals), safety and validation (check_mint/score_mint/verify_claim), execution (build_swap), and outcome auditing (track_record). Minor gaps exist, such as an EVM swap builder to complete the Robinhood check path, but the core workflow is usable.