Advan: Solana trading tools

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

With no annotations, the description carries the full burden and does well: it discloses cost ('Free'), that Advan never signs or holds keys, that the output is unsigned base64, and the downstream dependency on Jupiter's execute endpoint for MM co-signature. Gaps remain on rate limits, failure modes, and defaults for slippage/amount, but the safety and custody profile is unusually clear.

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?

Front-loaded with the key fact ('Free. Returns an UNSIGNED base64 transaction'), then custody guarantee, then the flag semantics. Dense but every sentence carries information; the Jupiter endpoint reference is justified because it changes what the caller must do next.

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 7-parameter transaction-building tool with no annotations and no output schema, the description covers output shape and custody behavior but omits the meaning of most inputs and any default values. An agent could call it, but only by guessing at amount units and slippage behavior.

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 0% across 7 parameters, so the description must compensate and it largely does not. Only selfBroadcast is explained; taker, receiver, amount (string in base units?), inputMint/outputMint, and slippageBps defaults are left entirely to the bare schema patterns.

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: returns an UNSIGNED base64 transaction for the taker wallet to sign. A reader knows exactly what the tool produces. It does not, however, name siblings like get_quote as a prerequisite or contrast itself with them, leaving differentiation implicit.

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 clear operational guidance on the selfBroadcast switch: default keeps JupiterZ routes requiring Jupiter POST /swap/v2/execute for co-signature, true excludes jupiterz for direct broadcast. It does not say when to use this tool at all (e.g., after get_quote) or when not to, so the caller-facing branch is covered but the workflow context is not.

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

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

With no annotations, the description carries the disclosure burden and does well: it identifies the endpoint, says it is free, specifies 'no taker', describes the returned fields, and explicitly states that no transaction is returned. It omits error behavior, rate limits, and auth details, but covers the key behavioral traits for a read-only quote call.

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 three compact sentences with the endpoint and key distinction front-loaded. Every sentence adds useful information, including the explicit non-return of a transaction.

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?

There is no output schema, and the description usefully summarizes the returned fields and explicitly says no transaction is returned. However, it leaves the four input parameters undocumented and does not address error cases or execution boundaries, so an agent can call it but must rely on the schema alone to understand the inputs.

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 0% and there are four parameters, yet the description does not explain inputMint, outputMint, amount, or slippageBps. It mentions that quotes include slippage, but not what the caller must supply or what units/constraints apply, so it fails to compensate for the schema's lack of parameter descriptions.

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 states a specific verb and resource: a free Jupiter Swap API V2 quote via GET /swap/v2/order with no taker. It also clarifies what the tool returns (amounts, route, slippage, referral fee fields) and what it does not return (a transaction), which distinguishes it from build_swap_tx.

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 note that it does not return a transaction implies this is a preview/quote step and that build_swap_tx is the execution step, but no sibling is named and there is no explicit when-to-use or when-not-to-use guidance. Usage is inferable but not stated.

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

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

With no annotations, the description carries the full burden and adds substantial behavioral context: exact cost ($0.02 USDC), payment protocol (x402 exact on a specific Solana network), data sources, and the error behavior for non-paying clients. It does not state whether the report is read-only or describe output/rate-limit behavior.

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 tightly written sentences front-load the core purpose and payment requirement, then add implementation and failure details. Every sentence contributes useful 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 paid, single-parameter tool with no annotations or output schema, the description covers the critical invocation context: cost, payment mechanism, data sources, and error behavior. It remains somewhat incomplete about what the returned risk report contains and how to interpret the mint parameter.

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 0% and the sole parameter, mint, has only a regex pattern with no description. The tool description does not explain that mint is a token mint address, its expected format, or what the value is used for, so it does not compensate for the schema 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 clearly identifies a token risk report and names the sources it combines (RPC mint/freeze authority, Jupiter Tokens V2, RugCheck). It implicitly distinguishes itself from siblings like build_swap_tx and get_quote, but does not explicitly name alternatives or state the action in verb form.

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?

It states the payment precondition and failure mode for clients that cannot pay, which implies when the tool is usable. However, it does not explicitly say when to use this versus a quote, swap, or portfolio tool, nor does it describe exclusions.

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

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

With no annotations, the description carries the full burden and does disclose the most important behavioral trait: this is a paid call costing $0.02 USDC via the x402 exact payment scheme. It also discloses the pricing oracle. It does not cover failure modes (invalid address, payment failure) or rate limits, but the payment disclosure is the critical missing piece in most definitions and it is present here.

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: the paid/cost constraint is front-loaded, then the returned data and its pricing source. 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 one-parameter tool with no output schema, the agent knows the cost, the payment mechanism, and the composition of the result. Remaining gaps (exact response shape, error behavior for malformed addresses) are minor.

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 0% for the single 'owner' parameter, so the description must compensate. Mentions of SOL, SPL Token and Token-2022 imply a Solana address, which is the key semantic, but the description never explicitly defines 'owner' or its expected format.

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 resource (wallet portfolio) and precisely what is returned: SOL plus SPL Token and Token-2022 balances, priced with Jupiter Price V3. Sibling tools (build_swap_tx, get_quote, token_risk) are clearly different operations, so no confusion arises, though it never names or contrasts them directly.

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?

There is no statement of when to call this versus alternatives, no prerequisites (e.g. wallet chain requirement), and no exclusions. The purpose implies usage, but the agent must infer everything about context.

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