Market Intelligence API

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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful behavioral context by stating the analysis is 'live', scoped to 'the last hour', and limited to DEX trade flow plus a computed verdict. No contradiction with annotations exists.

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, well-front-loaded sentence: the action comes first, followed by the temporal scope and a compact list of expected outputs. There is no filler or redundant information beyond useful clarification.

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 wisely enumerates the expected return fields: buy/sell volume, buy pressure, price change, largest trade, trader concentration, and verdict. Combined with the chain guidance and read-only annotations, this gives an agent enough context to invoke the tool correctly, though error behavior and edge cases are not addressed.

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?

With only 50% schema description coverage, the prose compensates by explaining the chain choices ('Base by default; also arbitrum, optimism') and clarifying that address is an ERC-20 token contract address. This adds meaning beyond the raw schema, though part of it is redundant with the schema's enum and default.

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 action ('send a token contract address'), the resource ('ERC-20 token'), and the exact output ('live DEX trade flow' with specified metrics and a 'verdict'). This distinctively separates it from sibling analysis tools like check_token_risk or get_symbol_intelligence, even without naming them.

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 usage: use this tool when you need live DEX trade-flow metrics for an ERC-20 token over the last hour. However, it does not explicitly state when to prefer this over alternative tools or mention any exclusions, so the when-to-use guidance is only implied.

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 annotations already indicate read-only, idempotent, non-destructive behavior, and the description adds meaningful context beyond those hints: walk-forward methodology and the no-look-ahead property ('Uses only prior buckets to build the baseline'). This gives an agent important information that annotations alone do not convey.

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, each carrying distinct and valuable content. The main action is front-loaded, the methodology detail is concise, and there is no redundancy with the schema or annotations.

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 rich annotations, optional parameters with defaults, and no output schema, the description mostly suffices: it explains the tool's purpose and its key methodological safeguard. Still, it does not explicitly state the return format or explain how the threshold parameters affect behavior, which would round out the picture.

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 50%, and the description adds no direct parameter-level meaning. Parameters like minConfidence and minBaselineSamples are not explained, and the 'prior buckets' note is not connected to the sampling parameters. An agent must infer semantics from names and defaults 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 opens with a specific verb, 'Validate', names the resource ('intelligence signals'), and lists concrete analyses (walk-forward forward returns, win rates, MFE/MAE, confidence calibration). This clearly distinguishes it from the get_* sibling tools, which are retrieval-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?

The description implies that this tool is for validating signal quality rather than for fetching market data, but it never explicitly states when to choose it over alternatives. It also does not name sibling tools like get_track_record that might serve a similar evaluative purpose, leaving selection somewhat 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?

Annotations already establish the operation is read-only and non-destructive, and the description adds substantial operational detail: simulated buy/sell honeypot check, owner/proxy/mint/blacklist/pause/fee checks, liquidity, LP burn, buy tax, flow, and verdict categories. No contradiction with annotations.

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

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

One dense sentence front-loads the purpose and then lists checks efficiently; every listed item is informative. It is longer than necessary but the list is a compact way to convey a broad analysis.

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 compensates by enumerating the checks and giving the verdict values. It does not specify exact output field names or structure, but it is sufficient for an agent to understand what will be returned.

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 50%; address semantics are already provided in the schema. The description names the supported chains and the default, but this mostly restates the chain enum/default rather than adding new meaning.

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 purpose (pre-purchase due diligence on an ERC-20) and a distinctive deliverable (a risk verdict plus a detailed list of checks). This clearly differentiates it from siblings like analyze_token and pre_trade_check.

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 'Due diligence before buying any ERC-20' gives a clear trigger for use, and the note about Base being the default clarifies scope. It does not explicitly name alternatives or when-not-to-use, so it falls short of a 5.

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

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

Annotations already establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds no further behavioral details such as output ordering, metric definitions, or limitations, but it does not contradict the annotations.

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

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

A single sentence with a strong verb, clear resource, and a concise list of the comparison axes. There is no filler or repetition of schema details.

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

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

For a two-parameter, read-only comparison tool with no nested objects, the description and schema together are nearly sufficient. The required symbols parameter has an example, the window has a sensible default, and the metric list implies the output nature, though exact return format is not specified.

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 symbols with an example and exposes the window enum, but the description adds no parameter-level meaning. It lists result dimensions rather than explaining how window or symbols affect the comparison, and schema description coverage is only 50%.

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 opens with the specific verb 'Compare' and names the resource, 'selected symbols', plus six concrete comparison dimensions. It is clearly distinct from a single-symbol intelligence tool, though it does not explicitly differentiate itself from related multi-symbol siblings like get_top_momentum.

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 intended use is implied: when you have a comma-separated list of symbols and want a comparative multi-factor read. However, there is no explicit when-to-use guidance, no exclusions, and no mention of alternative tools among the 29 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?

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description does not need to restate those. It adds some behavioral context by specifying 'high-confidence' and enumerating event types, but it does not explain how events are detected, ranked, or returned.

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 focused sentence with no filler, and the key action 'Find high-confidence market events' is front-loaded. It is concise, though it could be improved with a bit more structure around parameters and output.

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, no parameter explanation, and a large set of overlapping sibling tools, the description is incomplete for safe and correct invocation. An agent would not know what results to expect or how limit/window affect the search.

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 carries the burden of explaining limit and window. It does not mention either parameter, leaving the agent to guess what 'limit' limits or what 'window' controls.

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 finds high-confidence market events and gives concrete examples such as bullish accumulation, breakouts, and capitulation. However, it does not differentiate this tool from many overlapping siblings like find_opportunities, find_strong_buying, or get_market_regime.

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 its many siblings. No context is provided about which scenarios favor find_market_events over alternatives like find_unusual_activity or get_market_intelligence.

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

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

Annotations already declare read-only, idempotent, non-destructive behavior. The description adds useful behavioral detail beyond that: evidence grouped by independent source, typed risk factors, data quality, live 1h hit rate, and next calls to make. No contradiction with annotations.

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

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

Three dense, front-loaded sentences: the core action and output come first, followed by the usage directive and objective list. Every sentence earns its place and there is no filler.

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

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

With no output schema, the description compensates by enumerating the returned payload: ranked symbols, supporting/conflicting evidence by source, risk factors, data quality, hit rate, and next calls. Optional filter behavior and some parameters are left to the schema, but the core selection and use case are well covered.

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 64%, so the schema already documents most parameters. The description reinforces the objective enum and frames constraints generically, but it does not add significant per-parameter meaning beyond what the schema provides.

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 operation ('goal-driven scan') and the exact resource (ranked opportunity symbols with evidence and risk factors). The objective enum is spelled out, and the instruction to use it instead of chaining screeners differentiates it from specialized screener siblings like find_strong_buying or find_unusual_activity.

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

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

Explicitly tells the agent when to invoke the tool: when an objective and constraints are named, use it instead of chaining screeners. It does not spell out when-not-to-use or name a specific sibling alternative, so it stops short of a 5.

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

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

Annotations already cover readOnly, idempotent, open-world, and non-destructive behavior, so safety is disclosed. However, the description adds no behavioral detail such as how results are sorted, what threshold means operationally, or what the 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?

The description is a single, front-loaded sentence with no filler or redundant phrasing. It is appropriately concise for a straightforward screener.

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 three undocumented parameters, no output schema, and no mention of ranking or result format, the one-line description is insufficient for confident invocation. An agent can tell what the tool finds, but not enough about how to control or interpret the scan.

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 limit, window, and minBuyPressure have no descriptions. The phrase 'strong buy-side trade pressure' only hints at minBuyPressure; limit and window are left entirely to the agent's inference from names and 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 description uses the verb 'find' with a specific resource ('symbols with strong buy-side trade pressure'), and the phrase 'buy-side' cleanly distinguishes it from the sibling find_strong_selling. It is clear and immediately 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?

The description gives no guidance on when to use this tool versus siblings like find_strong_selling, find_unusual_activity, or find_opportunities. Usage must be inferred entirely from the tool name and general 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?

The annotations already cover read-only, idempotent, and non-destructive behavior, so the description carries a lighter burden. It adds the selection criterion 'strong sell-side trade pressure' but does not disclose how strength is measured, whether results are ranked, or how the scan behaves across different windows.

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 compact sentence with the operative verb and scope front-loaded. It contains no filler, redundancy, or irrelevant detail, making it appropriately sized for its purpose.

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 scanning tool with no output schema and three undocumented parameters, the description is too thin. An agent cannot predict the return format, ranking convention, or how window and maxBuyPressure combine to define 'strong sell-side pressure,' so correct usage relies on assumptions.

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 never mentions limit, window, or maxBuyPressure. Although parameter names and defaults hint at a lookback window and a buy-pressure threshold, the actual semantics—especially what maxBuyPressure means in relation to 'strong sell-side pressure'—are entirely unspecified.

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 ('find'), a clear resource ('symbols'), and a concrete filter ('strong sell-side trade pressure'). The phrase 'sell-side' also differentiates it from the sibling find_strong_buying, so an agent can distinguish the tool without inspecting the schema.

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

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

There is no guidance on when to choose this tool over alternatives such as find_strong_buying, find_unusual_activity, or find_opportunities. The intended use case is only implied by the name and one-line description, leaving tool selection mostly 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds some scoping by tying the search to anomaly score and minimum trade count, but it does not disclose output format, ordering, or response 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 a single concise sentence with no filler. It front-loads the action and resource, then immediately notes the key filtering logic.

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 all-optional, read-only tool, the description plus schema may be enough to invoke with defaults. However, with no output schema, it does not state what a returned result looks like or precisely what qualifies as 'trade activity,' leaving some ambiguity.

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 explains 'anomaly score' and 'minimum trade count' in relation to minAnomaly and minTrades, but leaves limit and window unexplained beyond their names and enum values.

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 ('Find') and resource ('statistically unusual trade activity'), and adds method hints via 'anomaly score and a minimum trade count.' It does not explicitly contrast with sibling find_* tools, but the anomaly-focused framing gives it a distinct purpose among them.

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 siblings like find_strong_buying, find_strong_selling, or find_opportunities. Usage context is only implied by the name and vague 'find unusual activity' phrasing, with 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?

Annotations already communicate a safe read-only, idempotent operation, so the description's job is lighter. It adds useful context about the returned metrics (aggressive buy/sell volume, buy pressure, VWAP, trade count), but it does not disclose output shape, pagination, or potential variability across symbols. No contradiction with annotations.

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

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

A single front-loaded sentence that immediately names the core deliverable, grounds it with examples, and lists the distinguishing metrics without repetition or filler.

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

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

For a simple one-symbol read operation, the description covers the main return fields and the annotations cover safety, but it leaves usage context and parameter details to be inferred. There is no output schema, so a bit more detail about response behavior would improve 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 description coverage is 0%, so the description needed to compensate, but it only illustrates the symbol parameter with examples and says nothing about interval selection or how limit behaves. The enum and default values in the schema carry most of the parameter meaning.

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 clear resource (OHLCV candles) and specifies the data fields included, with concrete symbol examples that make scope obvious. It lacks an explicit verb, though the tool name supplies it, and it does not explicitly differentiate from sibling tools like get_market_summary or get_symbol_intelligence.

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 prefer this tool over siblings or when not to use it. The description only states what data is returned; an agent must infer that this is the tool to use for candle data.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds meaningful context beyond annotations: the tool is free, operates at symbol-level coverage, and lists example data-source categories. This helps an agent understand expected behavior without contradicting the annotations.

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

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

One tightly worded sentence that front-loads the most important fact (FREE), states the output, gives concrete examples, and explains the purpose. 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 zero-parameter tool with rich annotations, this is nearly complete. It explains the return content and why an agent would use it. Without an output schema, it could add a bit more detail about the exact shape of the coverage result, but the examples and purpose are sufficient for effective 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 tool has zero parameters, so there is no parameter burden on the description. The schema coverage is effectively 100% because there is nothing to document. The description still clarifies what the no-argument call will return.

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 tool's output: which data sources cover each symbol, with concrete examples (spot on-chain DEX flow, perp venues). It is distinct from the sibling data-retrieval tools because it describes coverage metadata rather than market data itself. However, it does not explicitly name or contrast a specific sibling, so it stops short of 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?

The phrase 'FREE' and 'so you know what a paid call will return' implies the tool is a pre-flight discovery step before making paid API calls. This gives useful context but does not explicitly state when to use it versus alternatives, nor 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful context about the data scope (one UTC day, per venue) and included fields, but it does not disclose behaviors such as response shape, empty-data handling, or how venues are represented in the output.

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 informative sentence followed by a short purpose clause. It is front-loaded with the core data content and contains no filler or redundant 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?

For a moderately complex data-retrieval tool with no output schema, the description lists the returned fields and scope, which helps an agent understand what it will get. However, it omits practical invocation details such as how date and interval interact, what 'per venue' means in the result, and any caveats about data availability. The schema fills some gaps, but the description is not fully complete on its own.

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 33%, and the description does not compensate. It mentions 'for a symbol' but does not explain symbol format or accepted values, and it does not clarify the date or interval parameters beyond what the schema already states. The description adds little semantic value for the parameters.

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

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

The description clearly identifies the tool as returning one UTC day of trade-flow candles for a symbol, per venue, and enumerates the specific metrics included (OHLCV, aggressor volume, buy pressure, VWAP, trades). This is a specific verb+resource description that distinguishes it from generic candle tools like get_candles, though it does not explicitly name a sibling.

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 'For backtesting and research' gives an implied usage context, suggesting when an agent might choose this tool. However, it does not explicitly state when to prefer this over alternatives such as get_candles or backtest_signals, nor does it provide exclusions or 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?

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds meaningful context by specifying that data is read on-chain, which chains are covered, and the comparison against a 3-month Treasury bill. It also hints at the interpretive output around leverage demand, going beyond what the annotations alone provide.

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 that packs the essential elements: asset, protocol, chains, comparison benchmark, and interpretive angle. It is slightly run-on with a colon, but every part adds value and the most important information is 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, read-only tool, the description gives enough context: what is measured, where it is read, and what the spread indicates. It does not detail the exact return shape or whether the data is historical or current, but no output schema exists and the tool's scope is narrow.

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 and 100% schema description coverage, so parameter semantics are not a burden on the description. The baseline of 4 applies because there is nothing missing for an agent to invoke the tool correctly.

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 specific resource: USDC lending and borrowing APR on Aave v3 across five named chains, compared against the 3-month Treasury bill. It identifies the exact metric (DeFi vs TradFi dollar spread) and its interpretive angle (leverage demand), making it distinguishable from the broader market and treasury sibling tools.

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 its use case: when an agent needs the DeFi vs TradFi dollar spread and what it signals about leverage demand. It does not explicitly name alternatives or exclusions, but the context is clear enough given the unique scope.

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

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds meaningful context beyond annotations: the data source (SEC EDGAR), the focus on fundamental ratios, latest filing context, and a deterministic signal. It does not detail response shape or rate limits, but it does not contradict annotations and adds useful behavioral color.

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, information-dense sentence with no filler. The main action and resource appear first, followed by a compact list of output categories. Every clause contributes to understanding the tool's purpose and scope.

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 one required parameter and no output schema, the description names the input and the main output categories, which is largely sufficient. It could be more complete by explaining what the 'deterministic fundamental signal' means or by directing users to sibling tools for other intelligence types, but nothing essential to invoking the tool is missing.

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

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

The only parameter, symbol, is already fully described in the input schema with ticker examples. The description reinforces that it is a US equity but adds no new parameter-level semantics such as format constraints, accepted exchanges, or edge cases. Baseline 3 is appropriate given 100% schema description 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 states a specific verb ('Get'), a precise resource ('SEC EDGAR-derived fundamental intelligence'), and a clear scope ('for a US equity'). It enumerates the content areas (growth, margins, balance-sheet ratios, filing context, fundamental signal), which helps distinguish it from broader sibling tools like get_symbol_intelligence or get_market_intelligence.

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 clearly implies when to use this tool: when a caller needs SEC filing-based fundamental metrics for a single US equity. However, it does not explicitly name alternative siblings or state when not to use this tool, so exclusions and routing guidance are 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?

The description adds meaningful behavioral context beyond the annotations: it discloses the data source (SEC Form 4), the types of transactions included, and the possible signal values. This is consistent with the readOnlyHint, openWorldHint, idempotentHint, and destructiveHint annotations; no contradiction exists.

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 dense sentence that front-loads the core purpose and uses a compact list for outputs. Every element earns its place, and the signal enum adds practical value without fluff.

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

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

Without an output schema, the description carries a heavy burden for explaining return values; it does list key components and signal categories, which is helpful. But it omits the role of the `days` parameter in shaping the output and does not explain how the signal is derived or how results are structured, leaving meaningful gaps for a complex data 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?

The schema describes `symbol` but not `days`; the tool description only hints at recency through 'recent transactions' without explaining the `days` parameter, its default, or its effect on results. With schema description coverage at only 50%, the description does not compensate for the missing parameter meaning.

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 (SEC Form 4 insider trades) and enumerates concrete outputs such as open-market purchases/sales, 10b5-1 plans, per-insider totals, and a signal. It is unambiguous about the tool's domain but does not explicitly differentiate it from related siblings like get_smart_money or get_symbol_intelligence.

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 intended use case is implied by the domain: if you need SEC Form 4 insider activity, this tool provides it. However, there is no explicit when-to-use guidance, no mention of alternatives, and no statement about when this tool is preferable to a sibling.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds that the tool uses 'live trade activity' and multiple signal types, which provides some behavioral context beyond annotations. However, it does not describe output format, pagination, or any side effects. With annotations covering the safety aspect, a 3 is appropriate.

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, tightly-worded sentence that leads with the verb 'Rank' and then lists the criteria. There is no extraneous text, and it is front-loaded with the core purpose. Every word earns its place, making it highly concise and well-structured.

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 large set of similar sibling tools, no output schema, and zero parameter descriptions, the description is incomplete. It fails to explain what 'covered symbols' means, how the ranking is computed, how limit and window affect the results, or what the output looks like. An agent would struggle to disambiguate this from siblings and would not know what to expect in the response. This is a significant gap for a tool with this context.

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%, meaning the parameters (limit and window) have no descriptions in the schema. The tool description does not mention these parameters at all, so the agent receives no explanation of what 'window' means (e.g., time aggregation period) or how 'limit' affects results. The schema provides defaults and enums, but without any semantic explanation, the description fails to compensate for the coverage gap. This warrants a score of 2.

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 action (rank) and resource (covered symbols) and lists the criteria (live trade activity, pressure, momentum, acceleration, anomaly signals). This is clear and distinguishes it from sibling tools like get_top_activity or get_top_momentum, though it does not explicitly name alternatives. The verb and resource are specific, so it earns a 4.

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 does not provide any guidance on when to use this tool versus the many similar siblings (e.g., get_top_activity, get_top_momentum, find_unusual_activity). It does not mention exclusions or alternatives, leaving the agent to infer usage from the list of signals. There is no explicit when-to-use or when-not-to-use information.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds context about the result content (source attribution, publication time, symbols, sentiment) which is useful but not behavioral in nature. It does not describe side effects, rate limits, or prerequisites beyond what annotations imply, so it neither contradicts nor substantially enriches behavioral disclosure.

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 sentences with no filler. The main purpose is front-loaded, and the output highlights are succinctly listed. Every clause adds value.

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's enumeration of result fields is valuable. It covers the main categories (crypto, stocks, filings) implicitly and explains what to expect. However, it omits ordering, pagination, and parameter usage details, which are minor for a read-only news tool given the annotations already establish safety.

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 33% (only 'query' has a description). The tool description does not mention any parameter semantics, so it does not compensate for the gap. It leaves 'limit' and 'category' unexplained beyond the schema's type/enum, failing to clarify the meaning of category values or how query interacts with results.

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 verb 'Get' and the resource 'recent crypto and US stock news headlines and corporate filing events', and even enumerates the output fields (source attribution, publication time, extracted symbols, sentiment indicator). It is specific about scope but does not explicitly differentiate from sibling tools like find_market_events or get_market_summary, so it stops short of 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 provides no guidance on when to use this tool versus alternatives, nor any exclusions. It simply states what it does without mentioning conditions or routing to other tools. This leaves the agent to infer suitability from the name and context alone.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral details: the 15-minute delay, 5m candle interval, and included data fields, enriching the agent's understanding beyond the annotations without contradicting them.

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, well-structured sentence that leads with the most important selling point (FREE sample) and efficiently conveys the data type, delay, fields, and symbols. No unnecessary 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 preview tool with one parameter and no output schema, the description covers the essential aspects: data type, delay, content, symbols, and purpose. It does not specify the number of candles or time range, but this is minor for a sample.

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 has zero description coverage, and the only parameter (symbol) is fully enumerated with a default. The description merely repeats the allowed symbols without adding any new meaning or constraints, failing to compensate for the schema's lack of explanation.

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 provides a free sample of 15-minute delayed 5m candles with specific fields (close, USD volume, buy pressure) for ETHUSD or BTCUSD. It distinguishes itself from paid live tools and sibling candle tools by emphasizing its trial nature.

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 usage as a free trial before purchasing live tools, giving clear context. However, it does not explicitly name alternatives like get_candles or state when not to use it, leaving some inference to the agent.

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

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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the bar is lower. The description adds methodology ('trade-derived breadth and pressure') but does not disclose output format, limitations, or error behavior. It neither contradicts nor significantly enriches beyond annotations.

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

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

A single, front-loaded sentence with zero filler. It states the action and outcome immediately, making it highly efficient.

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 one-parameter tool with rich annotations, the description covers the core purpose and output categories, but omits usage context and parameter explanation. Without an output schema, it would benefit from a sentence on expected return values or when to use it.

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

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

Schema description coverage is 0%, so the description must explain the 'window' parameter, but it does not mention it at all. The enum values are self-explanatory as timeframes, but the meaning and effect of 'window' on classification are left unstated.

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 verb 'Classify', the resource 'covered market', and the possible outcomes BULLISH/BEARISH/MIXED. It also mentions the method 'trade-derived breadth and pressure', distinguishing it from market summary or news tools.

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 prefer this tool over siblings like get_market_summary or get_market_intelligence. There is no mention of context, exclusions, or alternatives, leaving the agent to infer usage from the name alone.

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

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

Annotations already declare the tool read-only, idempotent, open-world, and non-destructive, so the description need not restate safety. It adds useful context about aggregate market scope and data freshness, but it does not disclose window effects, caching, or return formatting. No contradiction with annotations.

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

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

A single compact sentence front-loads the verb and object and lists the report contents without filler. It is appropriately sized for a low-complexity tool.

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

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

For a read-only tool with one optional parameter, the description gives a reasonable high-level outcome and names the data it returns. However, it omits the window parameter's effect and returns no detail about output shape, and it provides no selection guidance among the many sibling market tools. This leaves some ambiguity 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% and the description never mentions the only parameter, 'window', or its enum values (1m, 5m, 15m). The parameter name and enum are partially self-explanatory, but the description fails to compensate for the missing field-level documentation.

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 ('market-wide' summary) and enumerates the content areas: breadth, buying pressure, momentum, unusual activity, and data freshness. This helps distinguish it from token-specific tools like analyze_token, though it does not explicitly contrast it with overlapping siblings such as get_market_regime or get_market_intelligence.

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 versus alternatives. The word 'market-wide' implies an aggregate snapshot, but the description does not say when to prefer it over find_unusual_activity, get_top_momentum, or get_market_regime, nor when it would not be appropriate.

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

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

Annotations already convey readOnly, idempotent, openWorld, and non-destructive behavior, so the description need not repeat those. It adds meaningful context about the specific outputs (open interest per venue, funding, 1h/24h change, crowded flag), but does not disclose additional behavioral traits such as data freshness, pagination, or how the spot flow component is calculated.

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 dense sentence that front-loads the resource and quickly enumerates supported examples and returned data. It is efficient despite being long, and every clause contributes information; a slight restructure could make it easier to parse quickly.

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 reasonably carries the burden of describing return values, and it lists the key fields: open interest long/short, funding, 1h/24h change, and crowded flag. It also clarifies the supported asset universe and venues. However, the phrase 'next to the spot flow' is left vague and some output formatting details are absent.

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 covers 100% of parameters and already gives examples like TSLA and XAUUSD for the symbol. The description adds more symbol examples and venue names, but this is marginal added meaning beyond the schema and does not substantially improve an agent's understanding of the parameter's format or constraints.

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 (perpetual futures positioning for tokenized stocks, ETFs, commodities) and what data it returns, including open interest, funding, changes, and a crowded flag. It is specific and informative, though it does not explicitly differentiate itself from sibling tools like get_market_intelligence or get_symbol_intelligence.

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 usage via the data it returns, but it does not explicitly state when to use this tool versus alternatives, nor does it mention conditions where a different tool would be more appropriate. With many get_* siblings, more guidance would help disambiguation.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds value by stating 'FREE' and 'live', and by detailing the exact data returned (hit rates, perp crowding). It does not contradict annotations. The only missing piece might be disclosure of update frequency or accuracy caveats, but given the annotation coverage, this is adequate.

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, no fluff. The first sentence front-loads the core data description, the second gives the purpose. Every word earns its place. The structure is efficient and scannable.

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 parameters, the description provides a solid overview of what data is returned. It covers the key dimensions: time periods (7/30/90 days), horizons (5m, 15m, 1h, 24h), grouping (by signal, by confidence), and the extra perp crowding record. It doesn't describe exact output formatting, but for a summary tool this is sufficient. A 5 would require more detail on units or structure, but this is not a significant gap.

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

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

The tool has zero parameters, so schema coverage is effectively 100% (vacuous). Per the rubric, a baseline of 4 is appropriate for zero parameters. The description doesn't need to add parameter info, and it doesn't. It does describe the output dimensions (horizons, grouping), which is more than expected.

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 exactly what the tool provides: live hit rates of published signals over multiple periods and horizons, broken down by signal and confidence, plus the perp crowding record. It is specific about the resource (signals) and the data returned, and it clearly differs from siblings like get_track_record or backtest_signals by focusing on hit rate summary.

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 a clear use case: 'Judge the signals before buying them.' This implies when to use it. However, it does not explicitly mention alternatives or exclusions, such as 'for backtesting use backtest_signals' or 'for detailed analysis use analyze_token.' The context is clear but lacks explicit routing away from 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, so the safety profile is known. The description adds non-obvious behavioral context: it returns addresses only, compares top wallets vs all wallets, and excludes specific actor types. It does not mention pagination or data freshness, but for a read-only tool with rich annotations, this is adequate.

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: the first packs the core content and output metrics, the second states exclusions. No filler, front-loaded with the main purpose, and 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?

Given a single required parameter, no output schema, and read-only annotations, the description provides sufficient detail for correct invocation. It lists return metrics, clarifies address-only results, and scopes the trader universe. Minor gaps like time windows are not critical for calling the tool 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?

Schema coverage is 100% with the 'symbol' parameter already described by examples (ETHUSD, BTCUSD, NVDA). The description adds the context that the symbol is traded on DEXes, reinforcing the meaning, but does not introduce new parameter requirements or format nuances. Baseline 3 is appropriate as the schema carries the semantic load.

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 the most profitable wallets trading a symbol on DEXes, with specific metrics (realized/unrealized PnL, win rate, holding time, net flow). It distinguishes itself by excluding arbitrage, MEV, bots, and routers, which differentiates it from generic market or activity tools. The verb is implicit in the name 'get' but the resource and 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?

The description implies when to use it (when you need smart money wallet flows for a symbol) but does not explicitly name alternatives or provide when-not-to-use guidance. The exclusion of certain wallet types is a scope clarification rather than usage routing. Sibling tools exist (e.g., get_top_activity, analyze_token) but no comparative direction is given.

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

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

Annotations already establish read-only, non-destructive, and idempotent behavior. The description adds the key behavioral fact of cost ('Cheapest call ($0.001)') and clarifies the return payload, which is useful beyond the structured annotations.

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

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

A single sentence front-loads the most decision-relevant fact (cost) and then states the scope and returned fields. There is no filler or redundant restatement of the 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?

With no output schema, listing the headline fields is valuable and makes the return shape reasonably predictable. The main gaps are the un-explained 'window' parameter and the lack of explicit guidance about when to choose this over sibling tools, so it is not 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 description coverage is only 50%, and the description adds no meaningful parameter guidance—especially for 'window', which is left entirely to the schema enum. The listed fields are outputs, not parameter semantics, so the agent gains little beyond the schema for using the parameters.

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

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

Description clearly identifies the tool as a low-cost, real-time single-symbol snapshot and enumerates the returned fields, which separates it from market-wide or historical tools. It lacks a direct verb and does not explicitly name sibling alternatives, but the resource and scope are specific.

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 '$0.001' cost and 'right now' imply the tool is for a cheap, immediate single-symbol check. It does not state when not to use it or name alternatives, so usage context is only implied, not explicit.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered by structured data. The description adds modest behavioral context by specifying 'latest,' 'trade-derived,' and single-symbol scoping, but it does not explain refresh behavior, data sourcing, or limitations. This is acceptable given the annotations, but not richly transparent.

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 compact sentence with no filler. It front-loads the action and core scope while keeping every word functional. There is no redundancy, and the structure is ideal for quick agent consumption.

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 parameter descriptions, the description carries a heavy burden that it does not fully meet. It tells the agent what the tool is broadly for, but not what the response contains or how the optional window affects the result. Given the large sibling set, an agent may still be uncertain whether this tool is the right one for a specific intelligence need.

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 needs to compensate, but it only reinforces the 'symbol' parameter with the phrase 'one symbol.' It does not explain the optional window parameter, its allowed 1m/5m/15m values, or what the window controls. An agent invoking the tool correctly would benefit from knowing that window selects the trade-derived aggregation timeframe.

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

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

The description uses a specific verb and resource: 'Get the latest trade-derived intelligence for one symbol.' It clearly indicates a single-symbol scope and the 'trade-derived' qualifier helps distinguish it from fundamental or market intelligence siblings. However, 'intelligence' remains somewhat abstract and doesn't define what the returned insight actually is, so it stops short of 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 phrase 'for one symbol' implies a single-asset query, which gives some context, but there is no explicit guidance about when to choose this tool over related siblings like get_fundamental_intelligence or get_market_intelligence. No alternatives or exclusions are mentioned, so the usage guidance is mostly implied rather than stated.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds useful behavioral context by saying the data is 24/7 and session-labelled, and clarifies the kind of signal being surfaced. It does not cover return structure or pagination, but for a read-only signal tool this is acceptable.

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 dense sentence that front-loads the core purpose ('24/7 trade flow') and then elaborates on the session labelling. It contains no filler, though it could be split into two sentences for slightly better scannability.

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 read-only tool with two optional parameterseb and no output schema, the description conveys the main data domain but omits what the limit and window parameters control and what the returned object looks like. The agent can call it correctly based on defaults, but not with full contextual awareness.

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 by explaining limit and window semanticsestr. It does not mention either parameter or how they affect the returned trade flow or sentiment data. The schema shows defaults and enums but provides no semantic meaning beyond allowed values.

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 it provides 24/7 trade flow and US equity/ETF sentiment, labelled with the current US market session. The resource and output type are identifiable, though it does not explicitly distinguish itself from closely related sibling tools like get_tokenized_stock_premium or get_market_intelligence.

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 usage contexts: overnight, pre-market, after hours, and weekends, which helps an agent decide when this sentiment/flow tool is relevant. However, it does not state when not to use it or name alternative tools for different data needs.

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

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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description only needs to add context beyond safety. It does so by stating bps units, the two output modes, and that symbol-mode returns per-US-market-session statistics. There is no contradiction with the annotations.

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

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

Two sentences deliver the core metric, the data sources, and both invocation modes with no filler. The most important identity information is 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 read-only data tool with four optional parameters, the two modes are described accurately, and the missing output schema is mitigated by stating that symbol-mode returns history with per-session statistics. It still leaves details like interval effects and exact statistic names unspecified, but an agent can select and invoke the tool correctly based on this definition.

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 descriptions cover symbol and symbols, and the prose clarifies the no-symbol versus symbol behavior. However, hours and interval have no schema descriptions, and the prose only weakly ties 'hours' to 'history' without explaining how interval or hours affect the response, so the description does not fully compensate for the 50% coverage gap.

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 an exact metric—'Price gap (premium in bps)'—and an exact resource: the same tokenized US stock across Robinhood Chain/EVM DEX pools and Solana xStocks pools. This specificity distinguishes it from siblings like get_tokenized_equities or get_defi_rate_spread even without naming them.

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

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

It gives clear conditional guidance for the symbol parameter: omit it for latest premiums across all paired stocks, provide it for per-session history. However, it never names alternatives or says when this tool should be chosen over sibling tools, so the decision remains partly implied by the tool name and unique scope.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by specifying the metric definitions (supply, 24h/7d net issuance) and the token list, which clarifies the data scope beyond the bare annotations.

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

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

A single sentence that front-loads the primary output (supply and net issuance), then lists constituents, then the intended interpretation (risk-on/risk-off gauge). Every clause earns its place with no redundant wording.

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, read-only tool with comprehensive annotations and no output schema, the description is complete: it states the metrics, the covered instruments, and the analytic interpretation. An agent has everything needed to decide when and how to invoke it.

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

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

The tool has zero parameters, so the baseline is 4. The description carries the full semantic weight by defining exactly what data the no-input call returns; no parameter documentation is needed.

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

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

The description uses a specific verb-resource pairing — reporting 'Supply and 24h/7d net issuance of tokenized treasury funds on chain' — and enumerates the exact constituents (BUIDL, USDY, OUSG, USTB, USYC). This is clearly distinguishable from siblings like get_tokenized_equities or get_treasury_auctions.

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 frames the tool as 'a risk-on/risk-off gauge', giving a clear decision context for when an agent should call it. It names the exact universe of funds covered, but does not explicitly contrast it with 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds the notion of 'relative trade activity' but does not disclose additional behavioral traits such as ranking order, inclusion criteria, or whether results are based on the selected window. It is consistent with annotations but does not go beyond them meaningfully.

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. It states the core purpose in ten words and earns its place in the definition.

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 read-only tool with two optional self-explanatory params, the description is minimally adequate but leaves gaps: it gives no sense of the result format, the meaning of 'relative trade activity', or how the window parameter affects behavior. Annotations cover safety, but an agent would still need to infer operational details.

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 by explaining what `limit` and `window` mean in context. It does not mention either parameter at all, leaving an agent to infer semantics only from names, defaults, and enum values. No added meaning is provided 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 a clear action ('find symbols') with a specific qualifier ('highest relative trade activity'), making the core purpose understandable. However, it does not distinguish this tool from close siblings like get_top_momentum or find_unusual_activity, so an agent may struggle to choose between them without opening schemas.

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

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

There is no guidance on when to use this tool versus its many siblings, nor any explicit exclusions or context. The description only states what it does, not when it should be selected over alternatives like find_strong_buying or get_top_momentum.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description need not restate safety. It adds a small behavioral cue with 'short-term' and 'strongest', implying a ranked list of high-momentum symbols, but does not disclose details like score calculation or filtering rules.

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-loads the core purpose. This is an appropriate size for a simple list tool.

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

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

The description plus schema and annotations give a basic picture, but it lacks parameter semantics and usage guidance. With no output schema, the description could be more explicit about ranking order or default behavior, though defaults are in the 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 0% and the description does not mention `limit` or `window`. An agent gets no help understanding that `window` controls the lookback period (1m/5m/15m) or that `limit` caps the result count, which are essential for correct use.

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 action ('Find') and resource ('symbols with the strongest short-term momentum score'), which is clear. However, it does not explicitly differentiate from sibling tools like get_top_activity or find_strong_buying; the term 'momentum score' provides some implicit 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?

The description offers no guidance on when to use this tool versus the many sibling screening tools, nor does it mention the `window` parameter for selecting a timeframe. There is no 'use this when...' or 'for X use ...'.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint: false, so the safety profile is covered. The description adds meaningful behavioral detail beyond that: the data is 'live,' hit rates are measured at 5m/15m/1h/24h, and it includes calibration buckets and latest signals with outcomes. It does not contradict the annotations.

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

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

The definition is a single dense sentence with no filler and front-loads the core subject before adding scope and options. It is slightly run-on, but each clause contributes useful information and nothing needs to be removed.

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 read-only data retrieval tool, the description communicates the main output content and the optional symbol filter. However, it omits the meaning of the 'window' parameter, does not specify how 'days' is bounded or interpreted, and there is no output schema to compensate for the missing response structure, leaving invocation partially underspecified.

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?

With schema description coverage at only 33%, the description needed to compensate, but it only clearly maps to 'symbol' via 'optionally for one symbol'; 'days' is only vaguely hinted by 'over the last days.' The 'window' parameter is left unexplained, and the listed output horizons (5m, 15m, 1h, 24h) do not obviously map to the enum [1m, 5m, 15m], creating ambiguity for an agent choosing a valid value.

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 a specific resource: the live track record of published signals, with hit rates at multiple horizons, calibration buckets, optional symbol scope, and latest outcomes. It goes well beyond the tool name and distinguishes the tool from generic market-data siblings, though it lacks an explicit verb like 'retrieve' and does not directly contrast with backtest_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?

The description implies the use case by emphasizing 'published signals' and 'outcomes'—evaluating live signal performance—and notes the optional symbol filter. However, it gives no explicit when-to-use versus alternatives, such as preferring backtest_signals for hypothetical strategies or this tool for live performance 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the derived 'change vs previous auction' context but does not disclose behavioral details like data source, update cadence, or response shape. No contradiction with annotations.

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

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

A single front-loaded sentence with no filler. The main object is stated first, followed by a compact list of value-adding details. 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?

With no output schema, the description partially compensates by listing the returned metrics, but it omits the response structure (array vs object, per-auction grouping) and does not clarify the 'days' parameter semantics. For a simple one-parameter read-only tool, it is adequate but has clear gaps.

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 only parameter, 'days', is not explained in the description. 'Upcoming and recent' hints at a time window, but the description never states how 'days' controls the lookback/lookforward range, leaving the agent to guess.

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 ('US Treasury auctions') and enumerates the exact data points returned: high yield, bid-to-cover, indirect/dealer shares, and change vs previous auction. This clearly distinguishes it from siblings like get_yield_curve or get_tokenized_treasuries, even though the verb is implicit rather than explicit.

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 temporal scope 'upcoming and recent' implies when the tool is relevant, but there is no explicit statement about when to prefer this over alternative sibling tools, nor any exclusion criteria. Usage guidance is reasonable but 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?

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds valuable behavioral context by enumerating the exact metrics returned (daily changes, slopes, inversion flags, breakeven inflation, overnight rates from specific sources). It does not contradict annotations and adds content beyond them.

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 dense sentence that packs in all key elements without fluff. It front-loads the core resource ('US Treasury par and real (TIPS) yield curve') and then lists specifics. While efficient, the long comma-separated list could be slightly better structured, but it remains concise and information-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?

With no output schema, the description carries the full burden of explaining the tool's return. It lists all major components: par and real curves, daily changes, slopes, inversion flags, breakeven, and overnight rates from specific sources. It is fairly complete for a no-parameter tool, though it doesn't specify units, as-of timing, or how the data is organized—minor gaps given the tool's simplicity.

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, and schema coverage is vacuously 100%. The description adds meaning by explaining what the tool returns, compensating for the lack of a formal output schema. It doesn't need to describe parameters since none exist.

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 ('get') and a precise resource ('US Treasury par and real (TIPS) yield curve') with detailed content (slopes, inversion flags, breakeven, overnight rates). It clearly distinguishes from siblings like get_treasury_auctions or get_market_summary by naming the exact dataset.

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 this is the tool for Treasury yield curve data but does not explicitly state when to use it versus alternatives (e.g., get_treasury_auctions for auctions, get_market_summary for a broader snapshot). No exclusions or alternative routing is provided, leaving selection 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?

Annotations declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context by specifying the output structure (verdict, score, checks) and the factors considered, which is beyond what annotations state. No contradiction with annotations.

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

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

The description is a single, well-structured sentence that front-loads the core purpose with an example, then lists the output and checks. It is not excessively verbose, though the list of checks adds length. The structure is effective 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 (synthesizing multiple market factors) and the lack of an output schema, the description adequately covers the return format and the main checks. It does not explain the meaning of the window parameter or the interpretation of the verdict score, but for a pre-trade check tool this is a minor gap. Overall, it is sufficient for an agent to call it correctly.

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

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

Schema description coverage is only 33% (only 'symbol' has a description). The description does not compensate: it mentions 'buy (or sell)' which mirrors the 'side' enum, but does not explain the meaning or impact of the 'window' parameter (1m, 5m, 15m) or the default behavior. With low coverage, the description should clarify these, but it remains silent, leaving the agent to guess.

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 function: it answers a pre-trade timing question for a given symbol and side, and returns a verdict with supporting checks. It names the specific output (FAVORABLE, CAUTION, UNFAVORABLE, score, checks) and lists the analysis components, making it distinct from sibling tools like get_market_regime or check_token_risk, which focus on individual factors.

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 'Right before a trade' provides a clear usage context, and the example question 'I want to buy (or sell) SYMBOL - is now a good moment?' tells the agent when to invoke this tool. However, it does not explicitly mention when not to use it or name alternative tools for different scenarios, but the context is strong enough.

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