Swap one token for another (app wallet, Jupiter)

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

Annotations already declare destructive/non-idempotent/open-world, but the description adds substantial context: real-money with no confirmation phrase, server re-quotes at execution so fill can move within slippage, and the fund output always returns to the same wallet. These are behavioral facts the agent cannot infer from the schema.

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?

Dense but front-loaded: the budget/real-money warning leads, followed by routing, use-case, exclusions, quote-first workflow, execution nuance, and verification. Every sentence carries actionable information with no filler.

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 money-moving tool with no output schema, the description covers the full burden: cost, routing, safety gating, quote-first workflow, execution re-quote, unit format, and a verification path via `app_wallet`. Nothing needed to invoke it correctly is missing.

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 description restates that amounts are RAW base units as a string, which the schema already covers, and adds only the slippage re-quote context — marginal value beyond the structured fields.

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 ('swap one token for another out of the app wallet') and immediately names the routing (Jupiter), the signing model (server-side), and where funds land (same app wallet). This cleanly separates it from siblings like swap_quote, deposit, and app_wallet_withdraw.

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?

Explicitly says when to use it ('whenever the user holds the wrong token'), names the negative case ('does NOT deposit into a fund (`deposit`)'), and mandates the quote-first flow with `swap_quote`. It even adds a safety rule about never acting on read text versus user instruction.

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