LCX Liberty DEX

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

With no annotations, the description carries the full behavioral burden and does so well: read-only, live, does not count against quota, only successful calls are counted, and at the limit calls are refused rather than billed as overage. These are exactly the traits an agent needs to reason about cost and rate-limit safety.

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 purpose and usage, then behavior, then return shape. It is dense and somewhat long, but each sentence adds distinct information, and the return-value detail is warranted given there is no output 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?

Without an output schema the description must describe the response, and it does: plan and planLabel, callsUsed, monthlyCalls, callsRemaining with the null-when-uncapped rule, and rateLimit as perSecond/perMinute with the note that a slow request consumes more than one. Nothing needed to call or interpret the tool 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?

Zero parameters, so the baseline is 4. The description usefully explains the empty schema by noting the calling key is implicit and no key or account id is passed, which confirms there is nothing to supply.

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 ('Reads the calling API key's own plan and usage') plus the scope constraint that no key or account id is passed. This is clearly distinguishable from the sibling tools (get_price, get_quote, list_chains, search_tokens), which are about market data rather than the caller's own quota.

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 names the triggering situations: answering quota or throttling questions, and checking before a long run of calls. No exclusions or named alternatives are given, but the siblings are unrelated, so the omission is minor.

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 so: it declares the operation read-only, enumerates the return shape (usd, change24h as a ratio with a worked example, source), and discloses freshness metadata (asOfBlock, ageSeconds, stale). It also explains graceful degradation ('usd is null and reason says why ... instead of an error') with concrete reason codes, which is behavior no structured field here provides.

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 earning its place: purpose front-loaded, then routing rules, then return/edge-case semantics. No restatement of the name and no filler despite the density of information.

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 two-param read tool with no output schema, the description covers the return fields, the units of change24h, staleness signals, and the null/reason no-price path. Combined with 100% schema coverage and sibling routing, an agent has everything needed to call it and interpret 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%, including a worked native-coin example and a full chainId legend, so the schema already does the heavy lifting. The description adds only the implicit framing of 'one whole token' as the unit (versus get_quote's amount), which is marginal beyond the structured fields. Baseline 3 is appropriate.

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+resource+scope: 'USD price of one whole token on one chain,' and qualifies the pricing source (LCX Liberty DEX indexed pools, real depth not mid-market). It explicitly distinguishes itself from siblings get_quote and search_tokens, so an agent can route without opening schemas.

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 when-to-use ('use it for a token's value'), names the alternative and its selection condition ('use get_quote for what a specific amount would swap for'), and supplies a prerequisite ('search_tokens first to turn a ticker into an address'). Nothing is left to 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?

With no annotations provided, the description carries the full burden and does so: it declares read-only and that it 'never executes a trade,' discloses the 0.5% slippage assumption, that a quote is priced at one block and lives 120 seconds, and enumerates the specific failure modes (no route, thin liquidity). This is exactly the behavioral context an agent needs before calling.

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 and the sibling routing are front-loaded, and the return-value and failure-mode sentences each earn their place. It is on the longer side for a single dense paragraph, but there is no filler or restatement of the title.

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 five-parameter read-only quote tool with no output schema, the description covers the return shape (output.amount, minimumAmount, decimals), optional fields (priceImpactPct, gasFeeUSD, venues, per-hop routes), and lifecycle metadata (blockNumber, expiresAt), plus error semantics. Nothing needed to call 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%, including unit rules for amount, the chain enum mapping, and the caveat about decimals_mismatch, so the schema does the heavy lifting. The description adds little parameter-level detail beyond what is already documented, though it does confirm amounts are returned in tokenOut base units with a decimals scale.

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 up front: 'Best route and expected output for selling a specific amount of one token for another on one chain.' It distinguishes itself from siblings by naming get_price (token value) and search_tokens (ticker to address) as alternatives rather than alternatives for the same 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 routing: 'Use it for what an amount would swap for; use get_price for a token's value, and search_tokens first to turn a ticker into an address.' This gives both the use case and the two prerequisite/alternative tools, with no inference required.

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 so well: read-only, takes no arguments, and does not count against the API key's quota. It also defines the semantics of ready, degraded, available, unavailableReason and ageSeconds against freshnessLimitSeconds, which is real behavioral context beyond a bare list.

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-loads purpose and usage before the field enumeration, and every clause earns its place given there is no output schema. The second sentence is dense but justified as the only documentation of the return shape.

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, so the description compensates by enumerating the returned fields and their meaning (chainId, router, ready, degraded, ageSeconds, etc.). For a zero-argument discovery tool this is complete enough to call 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?

Zero parameters, so the baseline is 4; the description correctly notes it takes no arguments and needs no param syntax. No further parameter meaning is required or missing.

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?

Opens with a specific verb and resource ('Every chain LCX Liberty DEX serves') plus the added dimension of live index health. An agent can immediately tell this apart from get_quote/get_price siblings, which it explicitly names.

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?

States exactly when to call it: to learn which chainId values other tools accept, to check whether a chain is quoting now, or to explain a refused/stale answer from get_quote or get_price. Alternatives are named and the selecting conditions are explicit.

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?

No annotations are provided, so the description carries the full burden and does so: read-only status, case-insensitive substring matching, empty-search fallback, ranking order (curated first, then pool count), symbol non-uniqueness, and the transfer-tax exclusion rule with its exact-address exception. These are non-obvious behaviors an agent could not 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?

Front-loaded with purpose and the routing hint, then behavior. It is a single dense block, and the ranking/edge-case sentences are long but each carries distinct information; a short bulleted break would read better, but there is little dead weight.

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 and no annotations, the description compensates fully by enumerating the returned fields (address, symbol, name, decimals, verified, poolCount, depthUsd), the hasMore pagination signal, and the native-coin zero-address convention. An agent has everything needed to call and interpret it.

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 is 3; the description still adds value beyond it by explaining what an omitted search does and how limit interacts with the hasMore flag, plus the ranking that determines which results arrive first. It stops short of adding format details the schema lacks, but nothing material is missing.

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 (finds tokens on one chain) plus the search keys (symbol, name, address), and explicitly distinguishes itself from siblings by naming get_quote and get_price as the consumers of its output. An agent can tell it apart from get_price/get_quote without opening any 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?

"Use it whenever you have a ticker or a name instead of an address" is an explicit selection condition that implicitly excludes the address-based siblings. It also resolves the ambiguous case with guidance: prefer the verified token or the one with most depth when a symbol matches several entries.

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