AgentData — crypto market data with a checkable record

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

With no annotations provided, the description must carry the full burden of behavioral disclosure, and it does not. It does not explain whether the tool triggers payment, returns historical or live data, imposes rate limits, or what the $0.005 USDC value actually represents. The parenthetical phrase is too ambiguous to be considered transparent 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?

The description is extremely short and contains no filler, frontloading the exchange list and threshold. However, its brevity borders on under-specification; it skips useful structuring such as what is returned. As concise phrasing alone, it earns full marks for economy, but not for informativeness, which caps it at a 4.

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 has minimal parameters and the rich payment flow is already captured in the parameter schema, which helps completeness. But there is no output schema and the description does not indicate the shape or count of returned opportunities, nor clarify the '0.005 USDC' as a filter or fee. Given the missing output semantics and the debut gate of the payment parameter, a minimum-viable score of 3 is appropriate.

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 single payment parameter is fully described in the input schema with a detailed explanation of the x402 flow, so the schema does the heavy lifting. The tool description itself adds no parameter-level meaning, only the ambiguous '$0.005 USDC' note, which may or may not relate to payment cost. The parameter semantics are adequate because the schema description coverage is 100%, meeting the baseline.

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 names the resource (cross-exchange spreads) and scopes it to four exchanges, but it lacks an explicit verb like 'returns' or 'lists', so it reads as a fragment rather than a clear statement of functionality. It also adds an ambiguous parenthetical '($0.005 USDC)' that could mean a fee threshold, a minimum spread, or something else, which clouds the purpose. It is distinguishable from many sibling tools by the 'arbitrage' scope, but the sentence itself does not confidently say what the agent will get.

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 no guidance on when to choose this over siblings such as get_crypto_prices or get_funding_rates. It does not mention typical use cases, prerequisites, nor when not to use it. The only context is the exchange list, which implies scope but not selection logic.

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 of behavioral disclosure. It mentions a cost ('$0.003 USDC') but does not explain the payment flow, whether repeat calls are needed, response behavior, or any other operational details that would help an agent anticipate what happens when invoking it.

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 very short and front-loaded, putting the metric first. It wastes no words and conveys its main function in one line, though the trailing cost in parentheses is slightly cryptic.

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, so the description should explain what the caller can expect in return. It only says 'TPS + block activity' without clarifying the exact shape, units, or freshness. The payment call-and-sign pattern is also not mentioned in the description, despite being important for actual invocation.

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 schema already covers the only parameter, payment, with a detailed explanation of the Base64 payload and signing flow. The description adds the cost amount, which is useful, but does compensate or expand much 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 description states the specific resource ('Base network') and the metrics it returns ('TPS + block activity'). This distinguishes it from other get_* sibling tools that target different data like gas prices or funding rates. It lacks a verb, but the tool name and content make the purpose reasonably clear.

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?

No guidance is provided on when to use this tool versus alternatives such as get_market_overview or get_gas_prices. The description only defines what data it returns, not under what circumstances an agent should select it.

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?

Even with no annotations, the description carries its weight: it discloses server-side cursor state keyed to the wallet, that it prevents re-downloading/re-diffing, and that the first call returns the last 24h. It leaves some behavior around payment requirements implicit, but the schema's payment parameter description covers that flow.

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 compact and front-loaded: the core value and differential are in the first sentence. The phrase 'Requires signal=' is a bit clipped, but no sentence is wasted and the description also lands key pricing and behavior facts.

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 has no annotations and no output schema, and the description does not describe the response shape or list expected return fields. This leaves an agent unsure what 'changes' looks like. The how and why of polling are well covered, but given no output schema, a little more on the returned data structure would be needed for full completeness.

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 baseline is 3. The description adds meaningful context by revealing the cost of the payment payload, wallet-keyed state, and the 24h initial time window, which helps an agent understand the payment parameter's purpose and how the signal cursor behaves.

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+resource: return only what changed for a given signal since this wallet last paid for it. It clearly differentiates from the many get_* sibling snapshot tools by calling itself a delta endpoint that is 'cheaper than any full payload' and a replacement for repeated polling.

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 explicitly explains when to use the tool: when you need incremental changes rather than a full payload, and as a replacement for repeated polling. It does not explicitly name sibling alternatives or state 'use get_<signal> for full data', but the contrast is clear enough.

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 main burden. It contains only the output type and price, not the payment-gating behavior, the need for an initial call without payment to receive signing requirements, or any computation or return semantics. The useful payment flow is relegated to the parameter description.

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 about eight words and front-loads the core output before appending the cost. There is no filler, no repetition of the tool name, and no redundant schema 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?

The description names the output and timeframe and the schema handles the payment parameter, which is enough for basic selection and invocation. However, with no output schema, no annotations, and no mention of which assets are covered or how the correlation matrix is shaped, the description leaves meaningful inference to the agent.

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% for the single optional payment parameter, and that description already explains signing, forwarding, and the initial unpaid call. The free-form tool description contributes no parameter semantics, so the baseline score of 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?

The description names a specific, unique artifact: a 30-day price correlation matrix, plus its cost. It distinguishes itself from the sibling price and technical tools, but it lacks an explicit verb such as 'computes' or 'returns', so it is clear rather than fully action-oriented.

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 guidance on when this should be preferred over alternatives like get_technical_indicators or get_historical, and no statement of the use case, such as detecting co-moving assets. The intended usage is only implied by the tool name and the phrase 'price correlation matrix.'

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 burden, and it adds a few behavioral clues: the data is real-time and there is a $0.002 USDC charge. However, the payment requirement and the call-without-payment-first behavior are expressed only implicitly or in the schema, not clearly explained in the tool description itself.

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 very short and front-loads the core value. The parenthetical cost note is ambiguous, so conciseness is achieved at some cost to clarity.

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 paid API with no output schema, the description is thin. It states the asset coverage and real-time nature, but does not mention the response format, the unit of returned prices, the payment flow, or the relationship to try_crypto_prices. The schema covers the payment payload, but the description does not fully contextualize the calling experience.

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 input schema already documents the payment parameter fully, so the baseline is 3. The description adds at least a cost clue ($0.002 USDC) beyond the schema, providing useful context for how payment should be configured, though the connection is not made explicit.

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 states the tool returns real-time prices for a specific, named set of assets (BTC, ETH, SOL, BNB, XRP), which makes its core purpose identifiable. It does not explicitly contrast itself with the sibling try_crypto_prices or other pricing tools, so it misses full differentiation.

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?

No guidance is given on when to use this tool instead of try_crypto_prices, get_market_overview, or get_historical. The parenthetical $0.002 USDC hints at a paid call but does not explain the required two-step payment flow or when the free/no-payment call should be made.

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 more responsibility. It does add the important behavioral fact that the call costs $0.003 USDC and names the covered protocols. It does not describe the payment handshake or result semantics, but the payment parameter already documents that workflow.

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 compact and front-loaded with the core subject and protocols before the cost. It is telegraphic and lacks a verb phrase, but every fragment carries useful information with no redundancy.

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 description is minimally viable: an agent can identify the resource, protocols, and cost. It is not fully self-contained because details like the sort criteria for 'top' and exactly what metric is returned are left implicit, but the schema fills in the payment interaction.

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%, and the single 'payment' parameter is fully documented with its x402/ERC-3009 flow and first-call behavior. The description adds the cost amount and protocol list, but does not materially explain the parameter 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 description names a distinct deliverable—top DeFi yields—and constrains it to Aave, Compound, Morpho, and Pendle, which is enough to separate it from pricing or funding-rate siblings. It relies on the tool's 'get' prefix for the verb, but the resource and protocol scope are unambiguous.

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?

No guidance is given about when to select this tool over the many sibling tools or when to avoid it. The protocol names imply the domain, but there are no exclusions, alternatives, or triggers such as 'when the user asks about lending APY'.

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?

There are no annotations, so the description must carry the behavioral disclosure burden. It hints at a $0.005 USDC cost but does not state that payment is required, that the call needs to be attempted once to receive payment requirements, or whether the operation is purely read-only.

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 extremely concise and front-loads the core purpose immediately. The parenthetical cost note is compact, and there is no wordy filler or restatement of the tool name.

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 description alone is too sparse for safe selection and invocation: it does not describe what the actual output will be, that this is a paid call requiring a signed payment payload, or how the first call without payment should be handled. The schema covers the payment argument, but the overall context is still insufficient without annotations or an output schema.

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 input schema has 100% description coverage, and the single payment parameter is already well explained in the schema. The description adds no parameter-level insight, which is acceptable given the baseline for complete schema coverage.

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 names a specific resource and action: a DEX vs CEX price comparison. It is distinct enough from sibling tools such as get_crypto_prices or get_market_overview, which cover broader or less differentiated pricing data.

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 implies when to use the tool: whenever DEX and CEX prices need to be compared. However, it provides no explicit guidance about when not to use it or which sibling alternatives might be more appropriate for broader price monitoring.

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?

There are no annotations, so the description must carry behavioral weight. It does disclose the key dimensions 'latest + 30-day history' and a cost of $0.005 USDC. However, it does not state whether a signed x402 payment payload is required, what the output shape looks like, or whether the tool is fully read-only.

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 one compact sentence with the data, units, lookback, and cost presented in a sensible order. Every word contributes to understanding or invoking the tool, with no filler or repetition.

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 single-parameter, paid data endpoint this is nearly complete: metric, units, asset universe, time span, and price are all present. The remaining gap is that no output response shape is described, and the signed-payment precondition is only evident from the schema, not from the tool description itself.

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 single payment parameter is already fully described in the schema, giving a baseline of 3. The description adds extra semantic value beyond the schema by explicit billing the cost: $0.005 USDC, which an agent cannot infer from the payment parameter description alone.

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 names a concrete resource: BTC & ETH ETF daily net flows, measured in USD millions, with a 30-day lookback. It also labels those flows as institutional demand, which distinguishes this from sibling tools like get_crypto_prices, get_funding_rates, or get_sentiment.

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 phrase 'institutional demand' provides clear context for when this tool is relevant: users investigating ETF-driven institutional flows in BTC and ETH. It does not explicitly mention alternatives or exclusions, but the domain is specific enough that an agent can route properly without deeper sibling comparison.

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 behavioral burden. It discloses the $0.003 USDC payment requirement, the x402/ERC-3009 payload workflow, and a key property: the server forwards the payload and never holds a key. It does not describe return-value shape, but the payment and auth behavior is clearly surfaced.

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 packs the essential facts into a single, efficient sentence: asset set, exchange, output focus, and price. It does not waste tokens or repeat schema detail. Every part earns its place.

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?

Given one optional, fully documented parameter and no output schema, the description and schema together provide enough context for an agent to bootstrap a call: first unpaid to get requirements, then paid with the signed payload. The only notable gap is that the return format is not detailed, but the description does hint at settlement-time output.

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 schema description coverage is 100%; the payment parameter is fully documented in the schema, including the two-call flow and what to sign. Since the description adds no further parameter semantics beyond what's already in the schema, 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?

The description states a clear resource—predicted next funding rate for BTC/ETH/SOL on MEXC—and adds a useful qualifier 'with time to settlement,' which helps distinguish it from the sibling get_funding_rates. It lacks a direct action verb like 'get' or 'fetch,' but the tool name and context make the operation evident.

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 the core usage context but does not explicitly say when to use this tool versus the very similar sibling get_funding_rates. The payment workflow in the input schema provides actionable calling guidance, but top-level usage alternatives are 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?

The description discloses the cost ($0.002 USDC), but does not state the payment-gated behavior: that the first call should be made without payment to receive requirements, that the second call must include signed payment, or what the resolver does with the payload. Without annotations, the description leaves an important gate for a human caller entirely implicit; the crucial details live in the input schema instead.

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 definition is spare in the best way: one short sentence, front-loaded with the core resource ('perpetual funding rates') and the expected signals, and then a single cost qualifier. No filler or repetition.

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 single-parameter tool with the payment flow fully documented in the schema, the overall definition covers everything essential to invoke it correctly: what data is returned, what the long/short signal aspect is, and how the payment argument works. It only misses a short relationships to try_funding_rates, which would improve routing but is not required to know.

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% and the single payment parameter already has a rich description covering the base64 x402 payload, ERC-3009 URI, the two-step signing flow, and the fact that the server never holds the key. The description's price mention adds economical context, but no new semantic detail 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 description identifies a specific resource in a clear noun phrase: perpetual funding rates with long/short signals. It still lacks an explicit verb, but it is appropriately distinguishable from siblings like get_funding_predictions because it targets rates rather than predictions.

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 'when to use this vs alternatives' guidance. It does not mention try_funding_rates as a trial/preview option, nor fund predictions as a related but different signal. The only procedural guidance is embedded in the parameter schema, which is about payment flow, not tool selection.

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 of explaining side effects, safety, and payment behavior. The '$0.002 USDC' parenthetical hints at a fee, but does not explicitly state whether the call is read-only, what the server does, or what happens on failure.

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 very short with minimal waste, but the parenthetical '$0.002 USDC' is ambiguous: it could be a fee, an output value, or a display format. It is compact but not as structurally clear as it could be.

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 single optional parameter is well documented in the schema, which helps, but the main description omits return-value shape and payment/workflow context. No output schema exists, so the description should say more about what the caller receives.

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%, and the optional payment parameter is thoroughly documented in the input schema, including the x402 flow and the no-key-held guarantee. The tool description adds no further parameter meaning, so the 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?

The description clearly identifies the domain: multi-chain gas prices across Base, ETH, and SOL. This is enough to distinguish it from sibling tools like get_crypto_prices, though it lacks an explicit verb such as 'returns' or 'fetches'.

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 explicit guidance about when to use this tool instead of alternatives. It merely labels the data domain, so an agent must infer usage from the tool name and the sibling list.

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 responsibility for behavioral context. It does disclose that the tool costs $0.010 USDC, which is a meaningful behavioral trait about payment requirements. However, it does not mention the two-step payment flow (call first, receive requirements, sign and call again) described in the schema, nor does it state any rate limits or side effects. The payment workflow is available in the parameter description, so the marginal behavioral disclosure is above baseline but incomplete.

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 extremely concise and front-loads the essential purpose and price in a single readable phrase. There is no wasted text. It loses a point because it is almost too sparse, providing no structural context such as a short sentence about typical invocation, though conciseness itself is strong.

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?

Given this tool has no output schema, no annotations, sparse parameter descriptions, and many sibling data tools, the one-line description leaves important gaps. An agent cannot tell how the returned candles are structured, whether the payment is per-request or per-candle, or how to distinguish this from similar market data retrievers. The two-step payment detail is in the schema, but the overall description does not make the tool self-sufficient especially without an output schema.

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 only 25% (only the payment parameter has a description). The tool description does not compensate by explaining interval, symbol, or limit, though the enum and defaults in the schema provide some hint. Given the low coverage, the description should have connected the params like interval/symbol to OHLCV semantics, but it simply does not.

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 'Historical OHLCV candles' clearly identifies the resource and the data type returned, and alongside the tool name 'get_historical' it is easy for an agent to infer this fetches past candlestick data. It distinguishes itself from sibling tools like get_crypto_prices or get_funding_rates by naming a concrete, unique object type (OHLCV candles). It loses a point because the description is a noun phrase rather than an explicit verb-driven sentence saying 'get' or 'fetch'.

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?

No guidance is given about when to use this tool compared to sibling tools such as get_crypto_prices, get_technical_indicators, or get_signal_history_*. The description does not state any context, exclusions, or alternatives. The word 'historical' implies it is for past data, but this is left to inference rather than explicit direction.

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 of explaining behavioral expectations. It hints at cost with '$0.003 USDC' and labels the result as 'estimated', but it does not disclose the paid x402 flow, the need to call once without payment, or whether this operation spends funds before returning data.

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 extremely compact and front-loaded: it names the subject, the scope, and the price with no wasted words. The parenthetical cost is terse but effectively communicates the paid aspect.

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 conceptually simple and has only one optional parameter, but the description omits the underlying asset or outcome format and leaves the payment authorization flow entirely to the schema. It is minimally viable but an agent might not know the tool requires payment before a meaningful response, or what shape the estimated liquidation zones take.

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%, and the payment parameter's own description thoroughly documents the handshake and security properties. The main description adds little beyond the '$0.003 USDC' pricing hint, so it provides no extra parameter meaning on top of a strong 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 description specifically states the resource ('liquidation zones') and the key dimension ('by leverage 5x/10x/20x'), which meaningfully expands on the tool name. It does not explicitly include a verb like 'returns' or 'gets', and it does not distinguish it from get_support_resistance or other price-level siblings.

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 guidance on when to prefer this tool over alternatives, no exclusions, and no prerequisites described. The description's mention of specific leverage levels implies a use case, but it never states a decision rule or context.

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?

There are no annotations, so the description itself carries the behavioral disclosure burden. It does reveal a fee/trending cost of $0.003 USDC, which is useful, and the schema separately discloses the payment flow and key handling. However, it does not clarify whether the operation is read-only, what side effects payments have, or how the returned data behaves.

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 a single sentence and front-loaded with the tool's purpose. It uses a terse list effectively, though the parenthetical 'trending ($0.003 USDC)' is ambiguous and could be clearer.

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 tool with no output schema and one optional payment parameter, the description lists the expected data categories well. Still, it lacks usage guidance, no explicit output shape, and leaves the meaning of 'trending ($0.003 USDC)' unresolved, especially against a large sibling set with overlapping macro/on-chain tools.

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 payment parameter is already fully documented in the input schema. The description adds the contextual cost figure, but it does not explain the parameter mechanics beyond what the schema provides. 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?

The description clearly identifies the resource as macro & on-chain context and enumerates its concrete content: stablecoin supply, BTC/ETH dominance, Fear & Greed, BTC network fundamentals. It avoids tautology, but it lacks an explicit verb and does not directly differentiate itself from overlapping siblings like get_stablecoin_health or get_market_overview.

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 content list implies when the tool is relevant, namely when an agent needs macro or on-chain context. However, it offers no explicit guidance about when to prefer this tool over siblings and provides no exclusions or alternative routing.

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. It does disclose that a payment of $0.003 USDC is required, which is useful, but it does not tell the agent that the first call without payment returns payment requirements rather than the overview, nor does it describe what a successful response looks like.

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 packs the resource, content, and cost into about ten words with no filler. The word 'full' is slightly vague, and the abbreviation 'arb signals' may not be immediately understood, but overall the text is efficient and earns its place.

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 an endpoint with just one optional parameter fully documented in the schema, the definition is almost adequate. However, with no output schema, the description says only that the agent will get a 'full market overview' without any sense of the response shape or how the returned data is structured; it also fails to flag the unusual two-step pay-then-call flow.

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 only parameter 'payment' is already described in the schema with 100% coverage: Base64 x402 payload, ERC-3009 TransferWithAuthorization, USDC on Base, plus the two-call flow, so the baseline is 3. The description adds the specific fee ($0.003 USDC), information the schema does not carry, which helps the agent judge the financial implication of the payment.

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 the resource (market overview) and its key contents (sentiment + arbitrage signals), with a clear price tag. It is distinguishable from most siblings, though it does not contrast with get_market_pulse, which could plausibly be the same kind of aggregate view.

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?

No guidance is given about when to use this tool rather than get_market_pulse, get_sentiment, or get_arbitrage_opportunities. With 29 get_* siblings, an agent must guess which one fits the task, since the description only says what it returns, not why it is the right choice.

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 partially discloses a significant behavioral trait: this tool requires a payment of $0.018 USDC and makes a single settlement. However, it does not explain the two-step payment flow (call without payment to get requirements), what happens on a failed payment, or any other side effects. The parameter schema fills some gaps, but the main description still does not give a complete behavioral picture.

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?

One sentence with no filler, front-loaded with the key value (price and '8 signals in one call') and supported by a compact list of the signals. It is structured well for scanning, though the long list of signal names makes it slightly dense.

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?

Given there is no output schema and no annotations, the description should explain what the tool returns and how payment works. It lists the eight signals and the one-payment behavior, which is helpful, but it does not describe success/error responses, call flow steps, or whether the first call without the payment parameter returns requirements. The parameter schema compensates partially, but completeness remains moderate.

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 schema coverage for the single 'payment' parameter is 100%, with a detailed description covering the Base64 payload and ERC-3009 flow. The description adds extra meaning by specifying the exact price ($0.018 USDC), which is useful and not present in the schema, helping the agent understand the payment amount and context.

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 communicates that this tool is a bundle of 8 specific market signals, listing them precisely. It distinguishes itself from the sibling signal-specific tools (e.g., get_sentiment, get_volatility), but it lacks a strong explicit verb like 'retrieve' or 'get,' relying on the tool name for the action.

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 implies use of this tool when multiple of the eight listed signals are needed, comparing the cost and settlement count with buying separately. It does not explicitly state exclusions or when to prefer single-signal tools, but the cost comparison gives clear context for choosing this bundle over the individual siblings.

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 of behavioral disclosure. It openly states that missing data is reported as 'unknown' rather than a pass, and that each verdict is filed as a claim and scored publicly after 7 days – important transparency about how results are generated and validated. It does not mention the two-step payment flow (covered in the schema) or any side effects, but it does meaningfully disclose the tool's honesty policy.

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 dense but every sentence earns its place: it states the output scale, the criteria, the unknown-handling policy, and the calibration mechanism. It is front-loaded with the core purpose and then adds specifics without any fluff. The structure is logical and easy to parse.

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?

Given the tool's complexity (multiple risk factors, no output schema), the description provides substantial context: it enumerates the criteria, the verdict levels, and the transparency policy. It does not describe the exact output structure (e.g., fields in the verdict), but it says 'with every finding behind it', implying detailed output. The payment flow is in the schema, so not repeating it is acceptable. The only gap is handling of invalid or nonexistent tokens, but overall it is complete enough for an agent to understand what it will receive.

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% – every parameter (chain, token, payment) is already documented with type and format. The description adds no new semantic detail about parameters beyond reinforcing that the token is on Solana or Base. Since the schema carries the full parameter explanation, the description's contribution is minimal, keeping this at the baseline for high schema coverage.

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 states a specific verb and resource: 'get a risk verdict for one memecoin'. It enumerates the specific risk factors considered (liquidity, mint authority, honeypot, sell tax, lock, concentration) and the output scale (LOW to CRITICAL). It is unambiguously distinct from sibling tools like get_new_memecoins (discovery) or get_market_overview (broad market).

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 makes it obvious when to use this tool: when an agent needs a risk assessment for a specific token on Solana or Base. It does not explicitly name alternatives or state when not to use it, but the specificity ('for one token') and the listed criteria clearly imply its scope. No misleading or exclusionary information is present.

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 burden and does a good job: it reveals the 15-minute screening cadence, the $0.010 USDC cost, the output fields, and the relationship to the public track record. It does not explicitly state that the operation is read-only or describe side effects, but that is less critical for a 'get' tool and the payment behavior is covered in 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?

Two tight sentences with no filler. Key facts—scope, frequency, cost, and returned fields—are front-loaded, and the provenance sentence about the public track record adds useful context without bloating the description.

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?

Despite having no output schema and no annotations, the description mentions the main returned data points and operational constraints. It does not explain pagination, response format, or error cases, but for a straightforward read tool with three optional parameters, it is reasonably complete. Slightly more explicit when-to-use guidance would make it fully complete.

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 67%, with chain and hours already described and payment given a detailed explanation. The top-level description adds contextual meaning around the chain ('Solana or Base') and implies the payment cost, but it does not materially improve parameter understanding beyond what the schema already provides. This is adequate but not exceptional.

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 states the resource: new memecoin pools on Solana or Base, and specifies the returned contents (risk verdict, market at screening, 7-day claim status). It does not use an explicit verb like 'returns' or 'lists', and it does not directly contrast itself with sibling tools such as get_memecoin_risk, so it is clear but not fully differentiated.

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 guidance on when to use this tool versus alternatives, no exclusions, and no mention of what get_memecoin_risk or other siblings should be used for instead. The notes about screening frequency and payment cost provide context, but not selection criteria.

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 burden, and it does disclose price ($0.012 USDC), a settlement, and a stateful per-wallet aspect ('since this wallet last called it'). However, it omits the two-step payment flow and any authorization/failure behavior; these are only covered in the schema's parameter description, not the tool description itself.

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 sentences with no filler: the first front-loads the product and price, then lists contents; the second gives a crisp value proposition. Every word earns its place.

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 description tells the agent what data areas are included but not the output format or return structure, which matters given there is no output schema. The payment flow is covered in the schema, so an agent can still call it correctly. Overall adequate for a bundled read-oriented data tool, with a notable gap around response shape.

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 input schema already documents the only parameter (payment) thoroughly, including the call-without-it-once flow, giving 100% schema coverage. The description adds no parameter-level meaning beyond the overall price. 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?

The description identifies the tool as a decision-ready overnight risk brief and enumerates its contents (DEX-vs-CEX spreads, liquidation zones, funding predictions, sentiment, stablecoin health, recorded changes). This maps cleanly onto sibling tools, clearly distinguishing it as a bundle. The lack of an explicit verb is minor since the tool name supplies 'get'.

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 second sentence gives actionable selection criteria: 20% cheaper than buying the five parts separately and one settlement instead of five. This strongly implies using this tool when you want the full set and individual sibling tools when you need only a subset. It does not state exclusions, but the economic logic provides clear guidance.

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. It mentions the multi-exchange coverage and the $0.005 USDC price, which is useful, but it does not disclose that the tool likely requires payment to obtain full data (only implied by the price), what gets returned when called without payment, or whether it is a read-only operation. The payment flow is only in the schema, not the tool description.

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 core description is one efficient sentence covering data content, sources, and cost. It is front-loaded with the main subject. The schema contains more elaborate payment instructions — worth keeping there — though the description could have added a short 'requires paid access' hint without redundancy.

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?

Given no output schema and no annotations, the description should explain what a caller receives and what triggers. It reveals content and price, but not the expected outcome of the first (unpaid) call, the response structure, or failure modes. Useful but thin on the payment-required behavioral side.

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 fully documents the payment parameter. The description adds the cost detail ($0.005 USDC) but does not clarify the two-step payment workflow (call once, receive requirements, sign, call again). The schema carries the weight here.

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 is specific: 'Trader positioning' with concrete metrics (open interest, long/short ratios, funding) and the exact sources (Binance + CoinEx, $0.005 USDC). It clearly distinguishes its content from siblings like get_funding_rates or get_market_overview.

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 implies a use case — checking trader positioning as a sentiment/flow signal — but does not state when to prefer it over get_funding_rates, get_sentiment, or get_market_overview. No exclusions or explicit when-not-to-use guidance.

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 behavioral burden. It discloses only the USDC cost; it does not state that a payment payload is required, that the first call returns payment requirements, or what the returned sentiment data looks like.

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 compact, front-loaded, and every part carries information — resource and price. It could be improved by turning it into an explicit verb phrase, but it is not padded or wasteful.

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?

It is minimally adequate for a single-parameter tool: the cost is stated and the payment parameter is fully documented. However, there is no output schema, no description of the return shape, and no reference to the closely related try_sentiment sibling, leaving selection and first-call expectations incomplete.

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 single parameter has 100% schema coverage and is already well documented in the input schema: Base64 payload, ERC-3009, USDC on Base, signing flow, and the two-call pattern. The description does not need to add parameter semantics; 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?

The description names a specific resource — 'Fear & Greed + composite sentiment' — with its cost, which goes beyond the tool name. It lacks an explicit verb, but the get_sentiment name plus that resource makes the intent clear. It does not differentiate from sibling try_sentiment, so it is not a 5.

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 no guidance on when to use this tool versus siblings such as try_sentiment. The payment sequencing is documented in the parameter schema, but the description itself provides no usage context or 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 provided, the description carries the full burden. It discloses the methodology ('Every claim is written down before the outcome exists and scored afterwards from our own recorded series'), the cost ('FREE'), and the tool's role in signal trust assessment. It does not mention rate limits or return format, but the behavioral context is sufficient for an agent.

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 sentences, each earning its place: purpose, methodology, and usage guidance. It is front-loaded with the core purpose and contains zero wasted words.

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 simple tool with one optional parameter, no output schema, and no annotations, the description covers the concept, methodology, and usage intent. It does not detail the return format, but the agent can infer calibration metrics are returned. The description is complete enough for selection and invocation.

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% (the single 'days' parameter has a description: 'window, default 30'). The tool description adds no additional meaning about the parameter, so it scores at the baseline. The parameter is adequately documented in 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 description clearly states the tool's purpose: 'How often our own signals turned right, scored against a naive baseline.' It uses a specific verb+resource and distinguishes from sibling tools like get_signal_history_7d (historical data) and get_funding_predictions (predictions) by focusing on calibration accuracy.

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 provides explicit guidance: 'Read this before trusting any signal here — including to find out which ones we cannot yet justify charging for.' This tells the agent when to use the tool (before other signals) and implies its role in evaluating trustworthiness. However, it does not explicitly name alternatives or state when not to use it.

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?

The description usefully discloses the hourly granularity, 7-day limit, USDC cost, and the fact that the data cannot be reconstructed from public sources afterward. It does not explain the return format, pagination, or the two-step payment/payment-requirements flow, though the payment flow is described in the input schema. With no annotations present, the description only partially carries the behavioral transparency burden.

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 two short sentences that immediately state the core capability, time window, and cost. The final clause about non-reconstructability is a valuable differentiator, and no words are wasted.

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 2-parameter tool with full schema coverage, the description gives the essential duration and pricing context. However, because there is no output schema, the description does not clearly explain the response shape or expected data series, and it leaves sibling-selection inference to the agent.

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 input schema already provides 100% coverage, including signal examples and a detailed payment parameter description. The description adds little parameter-specific meaning beyond 'signal history', so the 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?

The description clearly names the resource: an hourly recorded derived-signal history for the most recent 7 days, and even adds the price. It distinguishes from 'public' data sources, but it does not explicitly differentiate from sibling tools like get_signal_history_30d or get_signal_history_full in the text itself. Overall, the core purpose is clear and actionable.

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 context is implied: use this when a recorded 7-day hourly signal history is needed and when public reconstruction is insufficient. However, the description provides no explicit when-to-use/when-not-to-use guidance and does not mention which sibling tool should be chosen for longer history windows.

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 must disclose behavioral context, but it only provides a domain and a price. It does not tell the agent whether this is a read-only observation, what the reported values mean, whether it uses live or historical data, or what happens before authorization. The price is useful, but the description does not carry enough of the behavioral burden.

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 a short, front-loaded phrase with no filler and no redundant restatement of the tool name. It loses a point because it is closer to a label fragment than a complete, structured explanation of what the tool will do and return.

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?

This is a paid, externally authorized tool with no output schema and no annotations, so the description should provide more context about response shape and invocation behavior. The payment flow is covered in the schema, but the actual health/depeg semantics is not detailed enough for an agent to fully predict 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?

The only parameter is fully documented in the input schema, including the ERC-3009 x402 payment flow and the call-without-payment first step. The description adds only a per-call cost cue, which is not parameter semantics, so the schema-driven baseline of 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?

The description names the monitored resource (USDC/DAI depeg status) and clearly signals a stablecoin-health tool, which distinguishes it from the broader market, price, and sentiment tools in the sibling list. It does not fully explain what the returned health output contains, so it falls short of an unambiguous, schema-replaceable 5.

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 no explicit guidance on when to call this tool instead of alternatives like get_crypto_prices or get_market_overview. The use case is only implied by the tool name and the phrase 'depeg monitoring'; there are no exclusions, preconditions, or instructions about the paid x402 flow.

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 shoulders the burden of behavioral disclosure. It only states the cost and the signal interpretation; it does not explain call-success behavior, whether paid calls are required, rate limits, or what output shape the agent should expect. The payment behavior is only revealed in the parameter schema, not the description.

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 one tight sentence that packs the core data, interpretation, and price point. It loses only a little polish due to the informal abbreviation 'circ' and the slightly dense 'overhang ratio' phrasing, but every phrase earns its place.

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 parameter-light getter, the description conveys the core output categories and signal meaning. However, with no output schema or annotations, the agent is left without details on which coins are considered 'major', what order/format the data is returned in, and how to interpret the overhang ratio numerically.

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?

There is only one parameter, payment, and the input schema describes it in detail (Base64 x402 payload, self-signed ERC-3009, first-call behavior, no key held). Schema description coverage is 100%, so the description does not need to add much. The description adds nothing about payment but also does not need to because the schema handles it.

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 the resource — circulating/total/max supply and circ/total overhang ratio per major coin — and labels it as a structural sell-pressure signal. It is distinct from all sibling metric tools (sentiment, funding, prices, etc.), though it relies on a noun phrase rather than an explicit verb like 'retrieves' or 'lists'.

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?

No guidance is given about when to use this tool over alternatives, when supply overhang is a relevant signal, or when a user should ignore it. Sibling tools are numerous and cover sentiment, funding, technicals, etc., so the absence of any selection guidance is a real gap.

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?

Because there are no annotations, the description carries the behavioral burden. It usefully discloses that the call costs $0.005 USDC and uses fractal analysis for S/R levels, but it does not describe the output format, the sign-and-pay workflow, or return/error behavior beyond what is implied by the name.

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 a single front-loaded sentence with no filler; every word contributes to purpose, method, or pricing. This is an appropriately sized description for a low-complexity getter.

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 tool with only two parameters and no required arguments, the description is close to adequate when supplemented by the payment schema and default symbol. Still, it lacks a description of the output and does not route the agent to related tools, so it is more minimum-viable than complete.

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 schema describes only the 'payment' parameter, leaving 'symbol' undocumented by both description and schema. The symbol parameter is inferable from the name and default of BTCUSDT, but the description adds no parameter-level clarity and does not compensate for the 50% schema coverage.

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 tells an agent that the tool computes support/resistance levels using fractal analysis, so the resource and method are clear. However, it relies on the abbreviation 'S/R' and does not explicitly differentiate the tool from related technical-analysis getters.

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 no guidance about when to choose this tool over alternatives such as get_technical_indicators or get_liquidation_levels. There is no statement of intended context, exclusions, or alternatives, so usage guidance is essentially absent.

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 must carry behavioral context. It reveals a per-call cost in USDC and a payment payload requirement, which is useful, but it omits any mention of the likely flow (call first without a payment token to get payment requirements, then re-call with the signed payload). It also doesn't disclose that the server forwards the payload and never holds a key, even though the schema's payment description does. The description is too short to fully disclose payment and failure 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?

The description is extremely concise: a short list of indicators and a cost. Nothing is wasted. It is not as richly structured as it could be; a single sentence with a verb would be clearer, but it remains scanable and adequate.

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 description covers what the tool returns and its nominal cost, which is the most mission-critical information. However, it lacks a mention of the two-call payment flow and any detail about return shape. Since there is no output schema and no annotations, one extra sentence about how payment is provided would meaningfully improve an agent's chance of invoking 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?

Only about 33% of parameters are described in the schema, so the description adds value by naming the computed indicators and payment requirement. The interval enum is self-explanatory and symbol has a default, so the agent can still call the tool correctly. Some details about payment flow are in the payment parameter description, but the description itself reinforces the cost.

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 names a concrete resource (technical indicators) and lists the specific indicators (RSI, MACD, Bollinger Bands, ATR), which distinguishes it from broader or sentiment-based siblings. It does not explicitly state 'retrieve' or 'get', but the tool name covers that verb. Overall, an agent can identify what this tool does and which type of data it returns.

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 implies the tool is used to fetch technical indicators for a symbol at a given interval, with a payment requirement. It does not explain when to choose this over similar siblings like get_volatility, get_market_pulse, or get_support_resistance. It also lacks explicit alternative/routing guidance, so an agent would rely on name matching and the indicator list.

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?

There are no annotations, so the description carries the behavioral burden. It does transparently signal that the call has a USD-denominated cost ('$0.002 USDC'), which is useful. However, it does not explicitly state that data is returned on first call versus a payment-requirements response, although the input schema does describe the two-step x402 payment flow.

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 a single, front-loaded phrase that states the metric, the asset scope, and the price with no filler. Every clause earns its place, and the missing details live in the parameter 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?

The description and schema together cover the metric, the assets, the payment flow, and the price, which is most of what an agent needs for this simple tool. However, there is no output schema and no statement about the return value, so an agent must guess whether the result is a percentage, a list of values, or a time series.

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 input schema has 100% parameter-documentation coverage: it fully explains the optional x402 payment payload, the signing requirement, and the server behavior. The description adds the exact price but not much about how to construct the payment parameter, so the schema rightfully does the heavy lifting.

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 names a specific metric ('24h volatility') and the exact asset universe ('BTC/ETH/SOL'), so an agent can tell this from the many price, sentiment, and technical-indicator siblings. Although it lacks a verb, the tool name 'get_volatility' supplies the action and the phrase names a concrete, measurable resource.

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 no explicit guidance about when to call this tool versus alternatives like get_technical_indicators, get_crypto_prices, or get_historical. It implies the context through the metric name, but it does not state exclusions, preferred use cases, or how to choose between volatility norms and related tools.

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 burden and does disclose rate limiting (30 req/min), the lack of payment, and that the response reveals withheld fields. It does not fully specify response structure or auth, but for a zero-parameter sample tool the key behaviors are covered.

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 short sentences, front-loading the free-sample purpose and price datapoint before the rate limit and paid alternative. Minor redundancy ('FREE SAMPLE' and 'no payment') and the slightly vague withholding line keep it from being perfect.

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 zero-parameter sample endpoint with no output schema, the description covers cost, rate limit, what the sample provides, and the paid alternative. The exact response format is only hinted at, but the stated purpose is to judge the format, so a more explicit schema is not essential.

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 input schema is empty and schema coverage is 100%, so there are no parameters to document. The description correctly adds context about what is returned rather than inventing parameter details; this is the baseline for zero-parameter 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 states a clear, specific deliverable: a free real-time BTC price sample, and explicitly names the purpose (judging format and source). It differentiates itself from the paid sibling get_crypto_prices by identifying that as the paid multi-asset version.

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 says this is the no-payment sample for evaluating format/source, and points to get_crypto_prices as the paid tool that adds ETH, SOL, BNB, and XRP. It could be slightly more explicit about using get_crypto_prices when multi-asset data is needed, but the routing is clear.

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 behavioral burden, and it delivers: it discloses cost (free), rate limiting (30 requests/min), scope (BTC only), and even that the response lists what the sample withholds. This goes well beyond the tool name and prepares the agent for what the call returns and what it omits.

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 deliver the core purpose first ('FREE SAMPLE, no payment'), then the rate limit, then the paid alternative and response behavior. There is no filler, and every sentence earns its place. The structure is efficient and 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 zero-parameter tool with no annotations and no output schema, the description covers purpose, cost, rate limit, the paid alternative, and the response's withholding behavior. It is nearly complete for correct invocation, though it does not specify the exact response format or units of the funding rate. These are minor for a free sample with no 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?

The tool has zero parameters, so there are no parameter semantics to clarify. The description implicitly confirms that no inputs are required by framing the call as a simple sample. A score of 4 reflects the baseline expected for a no-parameter tool.

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 'FREE SAMPLE, no payment: the BTC perpetual funding rate,' clearly identifying both the resource and the tool's sample scope. It also distinguishes itself from the paid sibling get_funding_rates by explicitly noting the paid version covers every tracked perpetual. An agent can immediately tell what this tool does and how it differs from nearby alternatives.

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 explicitly positions this tool as the free sample and points to the paid get_funding_rates as the option for broader perpetual coverage. It also states the 30 requests/min rate limit, giving a concrete constraint on when use is appropriate. This effectively routes the agent between siblings without leaving the decision 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, the description carries the full transparency burden. It discloses the rate limit (30 requests/min), the free/no-payment status, and that the response lists what the sample withholds. This is sufficient transparency for a simple read-only, parameterless endpoint.

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 short sentences deliver the key facts: free sample, rate limit, what the paid version adds, and what the response reveals. There is no filler or redundant restating of the tool name.

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 parameterless sample endpoint, the description covers the essential operational details: rate limiting, payment status, missing components, and the alternative tool. Since there is no output schema, a more exact return shape would help, but the description already notes that the response lists what is withheld.

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?

There are zero parameters and the schema is empty, so parameter semantics are not applicable. The baseline of 4 is correct because there is nothing for the description to compensate for.

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 the resource as 'the Fear & Greed component of market sentiment' and distinguishes it from the paid get_sentiment by naming what is withheld. The verb 'try' plus 'FREE SAMPLE' makes the action and scope immediately understandable.

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 explicitly names the direct alternative get_sentiment and states the difference: this is a free sample, while get_sentiment adds the composite reading and funding-derived component. It doesn't contrast with every sibling, but it gives clear context for the closest comparison.

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?

Even though no annotations exist, the description discloses key behavioral traits: it costs $0.010 USDC, has a 168-hour lifetime, and creates a server-side standing condition. It stops short of explaining cancellation, error handling, or the exact effect of payment failure, but the cost and persistent side effect are usefully revealed.

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 sentences and front-loaded with the most critical info: purpose, cost, and duration. Each sentence earns its place, including the alternative polling mechanism. No redundant content.

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 annotations and no output schema, the description gives a good high-level context but leaves out important operational details such as what the response looks like, whether a condition ID is returned, or how to know the registration was successful. It also leaves the undocumented params ambiguous. This is not fully complete for a paid, state-changing registration 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 coverage is only 50%, and the description does not compensate for the missing fields. It does not explain what 'signal', 'op', or 'threshold' mean or how they map to a condition. The generic phrase 'standing condition' does not make the parameter semantics clear.

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 states the action ('Register a standing condition') and the resource (the always-on server watching it), making the tool's purpose obvious. It also distinguishes itself from sibling getters and try_* tools, which are data-fetching operations.

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 explicitly describes when to use the tool (when an agent needs to wait without running) and points to watch_status as a free alternative to poll status. It does not enumerate all sibling alternatives, but the getter vs. registration distinction is clear from context.

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