Orkid Swap

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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, but the description adds substantive context beyond them: non-custodial, unsigned calldata returned for the depositor to sign, and the auth model (free with X-ORKID-API-Key header, or $0.002 USDC/call via x402). That pricing/auth disclosure is exactly the kind of operational detail annotations cannot convey. It does not mention quote validity/expiry, which limits it to a 4.

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 tight sentences: what it does and on which chains first, then the return shape and signing model, then cost/auth. No filler and the most decision-relevant facts are front-loaded.

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, no-output-schema read tool, the description covers the essentials: return shape (unsigned tx), custody model, chain scope, and access/pricing. Missing is guidance on quote lifetime and on the required follow-up action, which matters for a bridge quote that an agent will act on.

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 adds meaning by enumerating the supported chains by name (Base, Ethereum, Arbitrum, Polygon, Robinhood 4663) and by clarifying that the depositor is the signing wallet. It still leaves the numeric chain IDs unmapped to names, which would have closed the last gap for the originChainId/destinationChainId pair.

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 ('Get a non-custodial cross-chain bridge quote') plus the underlying provider (Across) and the supported chain set, so the agent knows exactly what it produces. It stops short of naming how it differs from the sibling orkid_quote, which is the most likely confusion point.

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 rather than stated: 'Returns unsigned transaction data — the depositor wallet signs and broadcasts' tells the agent this is a pre-signature quote step. There is no explicit when-to-use versus orkid_quote or orkid_swap_link, and no guidance on what to do after receiving the quote (e.g. re-quote before submitting).

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 declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered structurally. The description adds the substantive content categories (live same-chain swaps, bridge coverage, gasless minimums), but says nothing about freshness, pagination, or how 'live' is determined.

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?

A single front-loaded sentence with no filler; every clause names a distinct data category the agent will receive. Nothing is repeated from the title beyond what is needed.

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?

With no input parameters and no output schema, the description carries the burden of explaining what comes back, and it does so by naming the three result categories. A note on data freshness or response shape would close the remaining gap, but for a simple reference tool this is sufficient.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly signals a parameterless enumeration by framing it as a listing call.

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 ("List") with a clear resource ("chains") and scopes it to Orkid's supported networks, including bridge coverage and gasless minimums. It implicitly separates itself from the quote/link siblings by being a reference enumeration, though it never names an alternative explicitly.

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 only implied: an agent can infer this is the discovery call to make before quoting or linking a swap. There is no explicit statement of when to use this versus orkid_quote or orkid_bridge_quote, and no exclusions or prerequisites.

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 flag readOnly/openWorld/non-destructive, but the description adds real substance: gasless via Permit2, MEV-protected, non-executing, no key handling, and the pricing/auth model (X-ORKID-API-Key or $0.002 USDC via x402). That payment and auth detail is behavior an agent needs and annotations don't convey; minor gap in not covering rate limits or failure modes.

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?

Purpose is front-loaded in the first clause, followed by mechanics, chains, return handling, and cost in a tight sequence. Every sentence carries distinct 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?

With no output schema, the description correctly explains the meaningful return value (swapUrl) and what to do with it. Combined with chain scope, auth, and pricing, an agent has everything needed to call and act on the result.

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 token symbols/addresses, human-readable amount, and chain values are already documented. The description only restates the chain list, adding no syntax or constraint detail beyond the schema. Baseline 3 applies.

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?

Specific verb+resource: 'Get a live, non-executing swap quote from the Orkid solver network,' plus the chain scope. 'Non-executing' and 'send the user there to sign' separate it from an execution tool like orkid_swap_link, and 'swap' separates it from orkid_bridge_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?

Gives clear context: same-chain swaps only on the listed chains, and the agent must route users to the returned swapUrl rather than signing. It never explicitly names when to prefer orkid_swap_link or orkid_bridge_quote, so guidance is clear but not exclusionary.

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 declare readOnlyHint=true, so the safety bar is lower; the description still adds real value by stating the tool only produces a link, that signing happens in the user's own wallet, and that an X-ORKID-API-Key header is required. It does not say whether the URL is single-use or expires.

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 tight sentences, front-loaded with what is produced, then the action to take, then the auth requirement. No filler or repetition of schema details.

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?

With no output schema, the description does convey that the return is a link, but it never addresses that all four parameters are optional — an agent cannot tell whether omitting them yields a bare swap page or an error. For a 4-param builder tool that is a meaningful gap.

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 schema itself documents to/from/chain/amount, and the description only restates them as 'prefilled pair, amount, chain'. It mentions 'partner attribution', which has no corresponding parameter, adding mild ambiguity rather than clarification.

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?

Specific verb and resource: 'Build a hydrated Orkid swap URL' with the prefilled fields enumerated. It is clearly distinct from the sibling quote/chains tools by output type (a shareable link, not quote data), though it never names those siblings explicitly.

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?

'Send this link to the user — they review and sign in their own wallet' implies the use case (hand-off for user execution), but there is no explicit when/when-not and no routing against orkid_quote, which is the obvious alternative for an agent that just needs pricing.

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