prepare_buy

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

With no annotations, the description carries the whole burden and does so: it declares the non-custodial model (never holds a private key, never signs or broadcasts), the exact artifact returned (a base64-encoded transaction), the rejection conditions (stale/failed risk score, out-of-range USD size, breached daily/weekly caps), and how a human consumes the output. This is unusually rich behavioral disclosure for a mutation-adjacent tool.

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 sentences, each doing distinct work: what is built, what the server will and will not do plus how to use the result, then the refusal conditions. Front-loaded on the core action with no filler or repetition of the schema.

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?

No output schema exists, and the description compensates by naming the return value (base64 transaction) and the consumption path. Combined with the prerequisite chain and refusal conditions, an agent has everything needed to call this correctly and to explain the result, which is thorough for a 3-parameter tool.

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 schema already documents mint, usdAmount and slippagePct, including the $10–$20 bound. The description reinforces the sizing constraint via the [MIN_TRADE_USD, MAX_TRADE_USD] phrasing and the spend-cap context, but adds nothing about slippagePct semantics or default slippage behavior, so the baseline 3 holds.

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 ('Build an UNSIGNED buy transaction for a pump.fun token') and immediately scopes it as unsigned, which separates it cleanly from execute_buy (which would broadcast) and from prepare_sell. An agent can pick this out of a 17-tool sibling list without opening a schema.

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 explicit preconditions — get_risk_score must have been called recently for this mint and passed, and the size must fall in [MIN_TRADE_USD, MAX_TRADE_USD] and the spend caps — plus the downstream step (review/sign in your own wallet). It stops short of naming the post-signing sibling (execute_buy) or contrasting directly with prepare_sell, so selection is clear but not fully routed.

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