Chaos — OKX Perpetual Signals

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

With no annotations, the description carries the full disclosure burden. It usefully names the outputs (trade count, win rate, cumulative PnL, max drawdown), implying a read/compute operation, but it says nothing about cost/latency of replaying history, permission needs, or whether the run has any side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler; the action comes first and the return payload second. Nothing is 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?

There is no output schema, but the description compensates by listing the returned metrics. Gaps remain around what 'pages' controls, how much history is covered, and how the backtest relates to the live signal 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 0% for 3 parameters. 'for one symbol' loosely maps to the symbol param and 'over history' hints at depth, but the 'pages' parameter (1-4) is never explained and the interval param's role is left entirely to its enum. The enums on symbol and interval do much of the work, keeping this at a baseline 3 rather than lower.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Replay the position state machine over history for one symbol', and enumerates the returned metrics. This is clearly distinct from siblings like get_signal/get_signals, though it never names them explicitly to reinforce the difference.

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 guidance, no prerequisites, and no mention of alternatives such as get_signal. The agent must infer that this is the historical-evaluation counterpart to the live signal 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 full behavioral burden. It lists returned fields but says nothing about auth, rate limits, compute cost, caching, or whether indicators need a minimum bar count — behavioral traits an agent needs for a series-computation call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, with the core content listing front-loaded and the audience note placed last as a routing cue. No filler, though the content enumeration could be trimmed to make room for the missing parameter and behavior context.

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 partly compensates for the absent output schema by naming the indicator fields an agent will receive. But with no annotations, no output schema, and three parameters at 0% description coverage, the definition leaves the agent without guidance on `bars`/`interval` semantics or call behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description only obliquely maps to the parameters: 'one symbol' covers symbol, and 'series' hints at interval/bars. The crucial `bars` parameter (10–600, controlling series length) is never mentioned, and the ambiguity between 'Full indicator series' and a bounded `bars` argument is unresolved.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Full indicator series for one symbol') and enumerates the payload contents (trend line, CVD, MACD histogram, RSI zone, compression flags), which is far more informative than the title alone. It does not explicitly differentiate itself from siblings like get_kline or get_signal, so an agent must infer that this returns derived indicators rather than raw candles or precomputed signals.

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?

'For callers building their own model' implies a target audience and hints at when to prefer this over a pre-baked signal tool, which is genuine implied routing. However, it never names an alternative or states a when-not condition, so the agent must guess how it relates to get_signal/get_signals.

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 full behavioral burden. It usefully discloses the relative cost ('the cheapest call') and that values are raw OHLCV, but says nothing about auth requirements, rate limits, page/ordering behavior, or what 'limit' actually controls at the boundary.

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 short sentences, zero filler, with the resource definition front-loaded and the usage condition trailing. Every clause 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?

There is no output schema, so the description should hint at the return shape; it names OHLCV fields but not ordering, timestamp format, or how many rows 'limit' yields. Adequate for a simple read tool but leaves real gaps for correct 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 0%, so the description must compensate. It does clarify that 'symbol' means a base asset on a USDT perpetual (beyond the bare enum tickers), but 'limit' (10-1000) and its default/effect are entirely unexplained, and 'interval' relies only on its enum.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: a raw OHLCV candle series scoped to a single OKX USDT perpetual swap. The phrase 'compute your own indicators' implicitly distinguishes it from the sibling get_indicators, though it doesn't name that sibling outright.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use it when you want to compute your own indicators' gives a concrete selection condition and implies the alternative (a tool that returns precomputed indicators). No explicit when-not case or named alternative, but 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?

No annotations are provided, so the description carries the full behavioral burden. It usefully signals a point-in-time read ('current snapshot') that distinguishes it from historical/backtest tools, but says nothing about freshness/refresh rate, permissions, rate limits, or whether the snapshot can be stale or empty.

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 dense sentence with the resource front-loaded and no filler. The colon-delimited field list is efficient, though it reads more like a data inventory than a description of behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description must carry the return-value burden, and it partially does by listing the signal fields. However, it omits interval semantics and any behavioral caveats, leaving meaningful gaps for a two-parameter, zero-coverage 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 description coverage is 0%, and the description only hints at the symbol parameter ('one symbol'). The interval parameter (2h/4h) is never mentioned, so the agent gets no guidance on what timeframe selection means even though enum values are self-labeling.

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 (signal snapshot for one symbol) and enumerates the fields returned (trend-channel direction, CVD cross, price cross, position state, latest action), so the agent knows exactly what it gets. It implicitly separates this from the plural sibling get_signals via 'one symbol,' but never names the sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: 'for one symbol' suggests single-market lookup vs the plural get_signals, and 'current' contrasts with backtest_signal, but neither alternative nor any when-not condition is stated. An agent must infer the routing decision.

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 convey that the call returns the entire universe in one shot (no pagination, no per-symbol loop). It does not state that the operation is read-only, the likely payload size/cost, or any rate limits — meaningful gaps for an unfiltered bulk fetch.

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 short sentences, zero filler, with the return shape front-loaded before the usage sentence. Every clause 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?

With no output schema, the description must characterize the return, and it tells the agent the grain (one row per symbol) but not the columns of each row — an agent cannot tell whether a row holds indicators, prices, or signal scores. The single required param is at least covered implicitly, leaving the shape known but the content unknown.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but there is only one parameter whose enum values (2h, 4h) are self-documenting. The description adds that the interval is a single value applied across all rows, which is slightly more than the schema shows, but it does not explain what the interval represents (candle timeframe) or any defaults.

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 full market table — every supported symbol at one interval, one row each" states the resource and its scope (all symbols) precisely, which implicitly distinguishes it from the singular get_signal. It never names that sibling explicitly, so an agent must infer the distinction, but the scope wording is clear enough to avoid most confusion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use this to scan, filter or rank the market in a single call" gives an explicit use context and implies the bulk/cross-sectional workflow (as opposed to a per-symbol lookup). It stops short of naming alternatives or stating exclusions, so it is context without 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 usefully discloses that the call is 'Free' (implying no cost/credit consumption, unlike siblings), but says nothing about auth requirements, rate limits, or read-only semantics beyond the verb 'List'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, zero filler, with the sequencing advice ('call this first') front-loaded after the content summary. Every clause 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?

With no output schema, the description does the work of describing return content by naming symbols, intervals and data source. That is enough for an agent to know what it will get, though it does not describe the shape or format of the returned data.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing to document; the baseline of 4 applies. The description correctly does not invent parameter discussion for an argument-less 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?

Specific verb ('List') plus resource ('markets') and it enumerates what the listing contains: supported symbols, intervals and data source. An agent can immediately distinguish this discovery tool from the data-fetching siblings (get_kline, get_signal, backtest_signal).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit sequencing directive — 'call this first to discover what is available' — which is exactly the guidance needed for a zero-argument discovery tool. It stops short of naming a specific alternative or a when-not condition, so it is clear context rather than full routing.

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