SafeSwapGlobal Crypto Swap Quotes

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

Although annotations already declare readOnlyHint, destructiveHint false, and openWorldHint false, the description adds substantial context beyond them: 30-second edge caching, structured error responses for unsupported pairs or unreachable feeds, and directional asymmetry caused by destination network fee structures. It is fully consistent with the annotations.

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 front-loaded with the core purpose, then organized into clearly labeled sections for usage, parameter edge cases, and behavior. Despite its length, every section carries decision-relevant information for a tool with non-obvious ticker conventions and pair asymmetry.

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?

An output schema exists, so return-value explanation is unnecessary, and the description still covers error conditions, caching, read-only behavior, and tricky parameter rules. Nothing an agent needs in order to invoke the tool correctly appears to be 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 coverage is already 100%, but the description still adds meaningful semantics: the Distinct Asset Rule explains rejection behavior, Ticker Matching specifies case-insensitivity and the difference between 'USDT' for TRC20 and 'USDTERC' for Ethereum mainnet, and Directional Asymmetry explains why from/to produce different floors and reserves. These details go well beyond the schema.

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 first sentence states a specific verb ('Inspects') and enumerates the exact resources covered: minimum deposit floors, pool caps, miner fees, and liquidity depth. It also scopes the tool negatively ('without calculating conversion amounts'), clearly distinguishing it from get_swap_quote.

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 description gives an explicit USE WHEN section with concrete scenarios and a DO NOT USE section naming the sibling tool get_swap_quote. The agent can route between the two tools without inference.

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?

Annotations already cover the safety profile, but the description adds genuinely new behavior: 30-second edge caching of liquidity feeds, a JSON error object when the upstream feed is unreachable or the pair is unrouted, and the fact that out-of-threshold amounts still execute with 'within_limits' false rather than failing. That last detail is critical and unobtainable from the annotations.

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 purpose, then organized under labeled routing and behavior sections so an agent can scan for the relevant slice. Every bullet carries actionable information; the one redundant line ('Strictly read-only') is a single clause and does no harm.

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?

An output schema exists, so return values need not be respecified; the description covers the remaining failure modes (unreachable feed, unrouted pair), the limit-evaluation contract, and caching staleness. Nothing an agent needs to call this 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 coverage is 100%, so the baseline would be 3, but the description adds real routing semantics beyond the schema: 'USDT' resolves to TRON (TRC20) and 'USDTERC' is required for Ethereum mainnet, tickers are case-insensitive, and from/to must differ. The aliasing rule alone materially changes how an agent fills the parameters.

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 ('Calculates') plus the exact outputs (swap estimates, network fees, deposit limits, routing URLs) and scope (240+ multi-chain pairs). It is immediately distinguishable from the two siblings, one of which is even named for a different job.

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 'USE WHEN' and 'DO NOT USE' blocks, with both sibling tools named as the alternatives ('list_supported_currencies', 'get_pair_limits_and_fees') and the selecting condition spelled out (checking availability vs. limits without an amount). It also excludes fiat and bank transfers.

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?

Beyond the annotations, the description discloses latency (<5ms), response size (up to 15 non-paginated records), availability, and lack of external network dependencies. These details are consistent with readOnlyHint=true, openWorldHint=false, and destructiveHint=false.

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 front-loaded with the core return value and then organized into usage, parameter intent, and behavior sections. Despite its length, each section contributes actionable guidance for selecting and invoking the tool.

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 tool is simple with one optional enum parameter, annotations covering safety, and an output schema. The description still provides complete usage, parameter, and behavioral context, so an agent has everything needed to call 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?

Although schema coverage is 100%, the description adds meaningful intent: privacy and stablecoins narrow the catalog by functional class to reduce token consumption, while omitting the parameter or passing 'all' returns the full roster. It also explains that returned tickers are canonical and accepted by the quote and limit tools.

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 uses a specific verb and resource: it returns the catalog of supported blockchain assets, ticker symbols, and network standards. It is clearly distinguishable from the quote and fee siblings, which are explicitly named as alternatives for other tasks.

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 gives explicit USE WHEN conditions such as discovering supported coins, validating tickers, or displaying network options before calling quote or limit tools. It also gives an explicit DO NOT USE section and routes calculation and fee tasks to get_swap_quote and get_pair_limits_and_fees.

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