ensotrade

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

With no annotations provided, the description is the sole source of behavioral info. It notes the API key requirement (authentication), but fails to mention read-only nature, rate limits, or idempotency. Since the tool likely retrieves data, the lack of explicit safety guarantees is a gap.

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

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

The description is three sentences: definition, requirement, parameter clue. It is efficient and front-loaded with the tool's purpose. However, the first sentence is jargon-heavy, which might reduce readability for some agents, but overall concise.

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 presence of an output schema (context signals), the description adequately covers what the tool does and how to use the parameter. It references a glossary for deeper understanding, compensating for missing output details. Lacks error handling or edge case info, but sufficient for a simple 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 'coin' only as a string, but the description adds 'ticker e.g. 'btc'', which clarifies the expected format and provides an example. This adds meaningful context beyond the schema, though more examples or constraints (like case sensitivity) would be helpful.

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 defines the tool as computing 'Toxic Carry Score' and 'Open Interest Quality Index', specifying the nature of each (cost-of-leverage, price trend agreement). Use of specific financial terms distinguishes it from sibling tools, which have different focuses (e.g., explain_move, market_snapshot).

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 mentions a prerequisite (EnsoTrade Pro API key) and directs users to the market_glossary resource for interpretation, providing some context. However, it does not explicitly state when to use this tool vs. alternatives, nor does it warn about inappropriate use cases, leaving guidance implicit.

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

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

No annotations are provided, so the description carries the full burden, and it excels: it explains that the leg is a cost on capital moved, not turnover, warns about misinterpreting turns=1, discloses the deleted venue-ranking output, and states it requires an EnsoTrade Pro API key. These are important behavioral traits that are not derivable from the schema.

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

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

The description is long and uses all-caps for emphasis, but every section serves a purpose: use cases, core point, behavioral caveats, parameter meanings, and a requirement note. It is structured in clear thematic blocks, though it could be tightened without losing 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?

Given a complex financial concept, no annotations, and a schema that only lists defaults, the description provides everything needed: purpose, usage scenarios, limitations, parameter semantics, and behavior caveats. The output schema exists, so return-value details are not the description's responsibility. It is contextually complete for effective tool selection and invocation.

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

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

The schema provides zero description coverage, and the description fills the gap completely. It explains each parameter with examples and semantics: 'coin' as a ticker like 'sol', 'notional_usd' as order size in USD, 'side' as 'buy' or 'sell', and 'turns' as how many times the balance is turned before repatriating. This goes far beyond the raw schema.

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

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

The description clearly identifies the tool as computing the cost of the currency conversion leg when trading in a venue's quote currency versus the caller's USD. It gives concrete use cases ('what does it really cost me to trade $5M of SOL') and explicitly distinguishes itself by stating it does not recommend venues, unlike potential 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 provides explicit when-to-use guidance with real examples and an explicit exclusion: 'IT DOES NOT TELL YOU WHICH VENUE TO TRADE ON, and you must not present it as if it does.' This is strong, clear usage guidance that helps an AI agent decide when to invoke this tool versus alternatives.

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

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

With no annotations provided, the description fully carries the transparency burden. It discloses the exact metric (Amihud illiquidity), data window (~62 days), output structure, and the crucial statistical caveat that the effect is weak-but-stable with a split-half check. It also explicitly warns against overstating the results, which is exemplary transparency.

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?

Though the description is longer than average, every sentence serves a purpose: defining the tool, stating use-cases, explaining the metric, and providing essential caveats. The structure is logical, with the 'IMPORTANT' callout emphasizing critical limitations. No redundancy 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?

Given no annotations and an empty input schema, the description covers all necessary context: what the tool does, how to interpret the output, the statistical reliability, and even pricing. The existence of an output schema reduces the need to explain return fields, but the description already provides ample context for an agent to use the tool effectively.

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

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

The input schema has zero parameters, but the description enriches the output semantics by explaining that lower numbers are cheaper and by specifying the measurement formula. This adds meaning beyond the schema and fully compensates for the absence of parameters, exceeding the baseline for no-parameter tools.

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

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

The description clearly states the tool's function: it returns a session-level profile of when crypto is cheapest to execute, pooled across the coin universe. It uses a specific verb ('returns') and describes the resource (four UTC session blocks with execution-cost numbers). This is distinct from sibling tools, which focus on other market analyses.

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

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

The description provides explicit use-cases ('what time of day should I trade', 'when is crypto most liquid') and warns against inventing per-coin best hours, which serves as a when-not-to-use instruction. However, it does not mention any alternative sibling tool, so the guidance is strong but not fully differentiated from alternatives.

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

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

No annotations are provided, so the description fully carries the burden. It discloses that capacity numbers are an upper bound based on reported volume, that time-to-exit figures are optimistic, that an 'effective volume' adjustment was deliberately not shipped, and warns against presenting figures as adjusted or verified. It also notes the API key requirement and the live degeneracy_check, adding substantial context.

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 well-structured but slightly verbose, especially the paragraph explaining the 'effective volume' adjustment. Nevertheless, every sentence adds necessary value, and important caveats are front-loaded after a clear purpose statement.

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, the description covers what it returns, its key limitations, parameter definitions, usage examples, and a prerequisite (API key). With an output schema also present, this is fully complete for an agent to select and invoke 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?

The input schema has zero descriptions for its two parameters, so the description fully compensates by defining `coin` as a ticker like 'sol' and `position_usd` as position size in USD. It also reinforces the default behavior through context, making both parameters clear.

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

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

The description clearly states the tool measures 'how fast a crypto position can be exited and what it costs,' with explicit use-case examples ('how long to get out of $5M of SOL', 'can I exit this position', 'what's my liquidity risk'). It lists specific return components, distinguishing itself from siblings like execution_window or route_order.

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 direct usage guidance via examples of questions it answers, and the opening line frames when to use it. However, it does not explicitly mention alternatives or when not to use it, so it stops short of a full 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?

The description fully discloses behavioral traits: returns a ready-to-quote sentence plus structured signals (price, regime, funding, open interest, basis), data delay (real-time with API key, 15-minute delay otherwise), and the need for an EnsoTrade Pro API key. No annotations exist, so the description carries the burden and does it well.

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 moderately concise at about 5 sentences, all adding value. It's front-loaded with purpose and examples, then details output and parameter. Slightly longer than necessary but 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 tool has one parameter, an output schema (so return values are covered), and the description covers all key aspects (purpose, usage, parameter, output, auth), it is complete for an AI agent to select and invoke 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?

The input schema only specifies 'coin' as a required string with no description. The description adds essential meaning: 'coin = ticker like 'btc', 'eth', 'sol''. Since schema description coverage is 0%, the description fully compensates.

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 explains why a crypto coin is up or down using live order-flow and positioning, with specific examples like 'why is bitcoin down'. It distinguishes itself from siblings by focusing on causal explanation rather than raw data.

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

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

The description explicitly states when to use the tool (e.g., for questions about the cause of a crypto move) and provides example questions. However, it does not mention when not to use or name alternative sibling tools for comparison.

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

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

With no annotations, the description fully discloses behavior: oldest-first ordering, point caps (1000/1500), API key requirement, scalp coverage dependency on WDE panel, and field lists. It does not mention rate limits or detailed auth flow, but the provided details are substantial for safe invocation.

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 fairly long (~200 words) but each sentence conveys necessary information. It uses clear sectioning with backtick formatting for parameters. Could be slightly more terse, but given the complexity (two modes, many fields), it is well-structured and not verbose.

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 existence of an output schema (not shown), the description need not detail return values. It covers authentication, mode selection, parameter details, data availability limitations, and troubleshooting guidance. For a multifaceted tool with two distinct data sources, this is comprehensive.

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

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

The input schema has no enums or param descriptions (0% coverage), but the description compensates fully: it gives symbol examples, enumerates all valid fields for each timeframe, explains default and max for hours, and clarifies timeframe string values. This adds complete meaning beyond the bare schema.

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

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

The description clearly states it fetches raw time series for one field on one symbol, oldest-first and capped. It distinctly differentiates the two modes (scalp order-flow vs candle timeframes) and positions it as a preliminary exploration tool before test_formula, setting it apart from siblings.

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

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

The description explicitly says 'Use this to explore what a field actually looks like before wiring it into test_formula,' providing clear context for when to invoke. It also covers data availability caveats and alternative symbol/timeframe suggestions, though it does not explicitly list sibling tools that might be better for other use cases.

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

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

No annotations are provided, so the description carries the full burden. It notes that Bearer-auth with a Pro API key is needed for real-time data, implying behavior differences. However, it does not explicitly state that the operation is read-only or describe any side effects.

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

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

The description is extremely concise with two sentences and a note. Key information is front-loaded: first sentence defines output, second gives usage examples. No extraneous 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?

Given the tool's simplicity (one parameter, output schema exists), the description covers purpose, usage, parameter meaning, and auth requirement. The output schema handles return value details, so the description is 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?

With 0% schema description coverage, the description adds meaning by explaining 'coin = ticker e.g. 'btc'. This clarifies the parameter's format and gives an example, but it is minimal and does not specify case sensitivity or additional 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 it returns the current perpetual funding rate and crowding read for a crypto coin. The specific verb 'get' and resource 'funding' are present, and the description distinguishes it from siblings like 'carry_pressure' which focus on other metrics.

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

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

The description provides explicit usage examples like 'what's the funding rate on <coin>' and 'is funding positive', and mentions the auth requirement for real-time data. However, it does not state when not to use this tool or compare it with alternatives.

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

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

No annotations are provided, so the description must cover behavioral traits. It discloses that it requires authentication and implies a read-only operation, but does not explicitly state it is non-destructive or mention rate limits. It also does not describe what the output looks like beyond the listed metrics. This is adequate but leaves some gaps.

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 concise, with three sentences that each serve a purpose: stating what the tool does, giving usage contexts, and explaining the parameter. There is no redundant or unnecessary information.

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

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

Given the simple input schema (one parameter) and the existence of an output schema, the description is sufficiently complete. It covers the key aspects: what data is provided, how to use it, and authentication. It could be more detailed about the output format, but the output schema likely covers that.

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

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

The single parameter 'coin' is described as 'ticker e.g. 'btc'', which adds meaning beyond the schema's type definition. Since schema description coverage is 0%, the description compensates well by providing an example and clarifying the expected format.

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 that the tool provides positioning regime, open interest, and recent taker imbalance for a crypto coin. It uses specific verbs ('get') and identifies the resource ('crypto coin'). It also lists use cases ('new longs, short covering, fresh shorts, or deleveraging'), which distinguishes it from sibling tools like 'market_snapshot' or 'get_funding'.

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

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

The description explicitly suggests using the tool for 'crypto order flow', 'open interest change', and 'is this a short squeeze'. It also mentions authentication requirements (bearer-auth with Pro API key). However, it does not specify when not to use or provide alternatives, which would elevate it to 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?

Despite no annotations, the description reveals critical behavioral traits: 'size_exceeds_capacity is a hard wall, not a cost' and 'par_offset_bp is NOT charged as a cost' to prevent misuse. It also notes the API key requirement and the rotation of the cheapest venue with size.

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 detailed and front-loaded, with the essential purpose in the first sentence. While lengthy, structured callouts (CAPACITY, par_offset_bp) make it digestible.

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?

Covers cost in/out, venue comparison, capacity limits, basis deviation, and field semantics. With an output schema present, this description provides ample context for an agent to invoke 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?

The description defines the sole parameter: 'notional_usd = the size to price.' This adds meaning beyond the schema's bare number type, and it flags the API key requirement for using the tool.

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

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

The description opens with a specific verb+resource: 'What it costs, right now, to move USD into and back out of the stablecoins' — clearly identifying the tool's purpose. It also differentiates from siblings with 'No coin involved: this is the currency leg on its own.'

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?

Provides explicit use cases: 'Use for "what does USDT conversion cost", "is USDC or USDT cheaper to hold", ...' This is clear context, but no when-not or alternative tool names, so not 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?

With no annotations, the description carries full burden. It mentions 'right now' indicating real-time nature and API key requirement, but lacks details on data freshness, rate limits, or output format. Adequate but not thorough.

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, front-loaded with purpose, no wasted words. Every sentence contributes 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?

Given the tool's simplicity and that an output schema exists, the description covers main points. Could mention the output shape, but not essential. The usage guidance adds completeness.

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

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

Schema coverage is 0% and description does not explain the 'limit' parameter. While the parameter is simple, the description fails to add meaning beyond the schema, which is critical given no schema descriptions.

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?

Clearly states it performs cross-sectional momentum ranking across the crypto perp universe, identifying leading vs lagging coins. Explicitly distinguishes itself by recommending usage 'FIRST' before drilling with other 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?

Gives explicit context: 'Use this FIRST when asked to find a coin or what should I look at before drilling into one with the other tools.' Also notes the requirement of an API key. Does not list alternative tools but implies a workflow.

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

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

No annotations provided, so the description carries the full burden. It discloses that public calls receive delayed data and no directional call, while Pro API key users get real-time data and a validated funding-momentum signal. This is transparent about the tier-dependent 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?

Two sentences: first sentence lists the snapshot contents, second sentence explains the parameter and authentication differences. Front-loaded with key information, no wasted words.

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

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

Given the tool has an output schema (not shown), the description does not need to detail return values. It covers the parameter, authentication, and data differences. Slightly incomplete in not mentioning potential errors or rate limits, but overall comprehensive for a single-parameter tool.

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

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

Schema coverage is 0%, so the description must explain the parameter. It says 'coin = ticker e.g. btc', providing an example but not full semantics like case sensitivity or allowed values. This is adequate but minimal.

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 a 'One combined live snapshot' for a crypto coin, listing specific data points (price, 24h change, funding, open interest, perp basis, positioning regime). This distinguishes it from sibling tools like get_funding or options_chain, which are more 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 description explains different usage based on authentication: Pro API key for real-time data and directional signal, public calls get delayed price and no signal. However, it does not explicitly state when to use this tool versus specific 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?

No annotations are provided, so the description must convey behavioral traits. It discloses 'Rows stay separate' and 'Pro key required', but it does not state if the tool is read-only, what 'bounded' exactly limits, or what happens without a Pro key. This is partial but not comprehensive.

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 four short sentences, each providing distinct information: purpose, venue format, row behavior, and authentication requirement. No unnecessary words 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?

With five parameters, no annotations, and a minimal description, the tool is not adequately described for correct invocation. The output schema helps but does not cover parameter semantics. The description lacks detail on how to set parameters or what the output represents, making it incomplete.

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

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

Schema description coverage is 0%, so the description must compensate. It explains that venues should be comma-separated, but the remaining four parameters (coins, limit, impact_pct, venue_class) are unexplained. The description adds only a hint about limit via 'Bounded', leaving significant ambiguity.

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 says 'Bounded MASS scan' which is vague without knowing what MASS scan is. It provides some behavioral specifics like 'Rows stay separate' but does not clearly state the tool's core function or how it differs from sibling tools like mass_scan.

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 word 'Bounded' implies it's a limited variant of mass_scan, and 'Pro key required' is a prerequisite, but there is no explicit guidance on when to use this tool versus alternatives. No use cases or exclusions are 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?

The description discloses that a Pro key is required and emphasizes 'One result per exchange; no blend,' which clarifies output behavior. However, it does not explain what MASS computes, whether it is read-only, or any side effects. With no annotations, the description carries the full burden but only partially fulfills it.

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

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

The description is two sentences, compact and front-loaded with the core purpose. Every clause adds relevant information without extraneous detail.

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

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

Despite having an output schema, the description fails to explain the tool's acronym, parameter meanings, or usage context. With four parameters and no schema descriptions, the description is too sparse to allow an agent to correctly select and invoke the tool.

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

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

Schema description coverage is 0%, and the description only implicitly mentions venues ('one selected exchange or comma-separated exchanges'). It provides no explanation for the required 'coin' parameter or for 'impact_pct' and 'venue_class'. This is a significant 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 states 'MASS on one selected exchange or comma-separated exchanges' and clarifies 'One result per exchange; no blend.' This indicates a specific scan action over exchanges, though 'MASS' is not expanded. It partially distinguishes from siblings like mass_map via the 'no blend' behavior.

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

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

No guidance is provided on when to use this tool versus alternatives like mass_map or market_snapshot. The description implies it works on one or multiple exchanges but does not state exclusions, prerequisites (beyond Pro key), or comparison with 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?

No annotations are provided, so the description carries the burden. It discloses that the tool requires an API key (auth requirement) and lists returned data types. However, it does not state whether the operation is read-only, any rate limits, or side effects, leaving gaps in behavioral understanding.

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

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

The description is three concise sentences. The first sentence defines the tool's purpose and output, the second adds an important prerequisite, and the third defines the parameter. No wasted words.

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

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

With only one parameter and an output schema present, the description provides sufficient context. It lists returned fields (strikes, IV, greeks, fair-value gap) and covers authentication. Could mention pagination or data scope, but overall complete.

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

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

The schema has 0% coverage for the single parameter 'coin'. The description clarifies it as 'underlying ticker e.g. 'btc'', adding format and example. This compensates meaningfully for the missing schema description.

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 returns 'Full crypto options chain for a coin' and lists specific data fields (strikes, mark IV, greeks, fair-value gap). The verb 'full' implies retrieval of complete chain, distinguishing it from siblings like 'get_funding' or 'market_snapshot'.

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 mentions a prerequisite (EnsoTrade Pro API key) but provides no guidance on when to use this tool versus alternatives (e.g., other market data tools). It does not specify appropriate contexts or exclusions.

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

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

The description discloses the authentication requirement (Bearer auth with Pro API key) and lists the output fields. With no annotations provided, it does not explicitly state the read-only nature or any rate limits, but it provides reasonable context for an AI to understand expected 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 three sentences long, with the first sentence front-loading the core purpose. Each sentence adds value: what it does, authentication details, and parameter clarification. No superfluous information.

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

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

Given the tool has only one parameter and an output schema exists (but not shown), the description sufficiently covers prerequisites, parameter meaning, and a list of output fields. It provides enough information for an AI to correctly select and invoke the 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?

Despite 0% schema coverage, the description adds meaning by stating 'coin = ticker e.g. 'btc''. This clarifies the parameter's purpose and provides an example, compensating well for the lack of schema descriptions.

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 a full perp dashboard for a crypto coin, listing specific data points (mark price, index price, funding rate, etc.). This distinguishes it from siblings like 'get_funding' which likely only returns funding data.

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

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

The description mentions the requirement for an EnsoTrade Pro API key and gives an example of the coin parameter. However, it does not explicitly state when to use this tool versus alternatives such as 'market_snapshot' or 'get_funding', nor does it provide exclusion criteria.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly states the computation uses reported venue volume (an upper bound), that no effective-volume adjustment is applied, and that a Pro API key is required, preventing misuse.

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 well-organized with purpose, use cases, parameter definitions, and an important caveat. Every sentence delivers useful information without fluff, and the important warning is clearly highlighted.

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 an output schema present, return-value details are unnecessary. The description covers what the tool does, when to use it, parameter semantics, limitations, and auth requirements, making it self-sufficient for an agent.

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

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

Schema descriptions are absent, but the description thoroughly explains all three parameters: `coins` (comma-separated list, default universe), `participation` (fraction, default 0.10), and `limit` (max 40). This adds complete semantic meaning beyond the raw schema.

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

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

The description clearly defines the tool as a position-limit table for crypto perps, specifying the computation (largest position exitable within 24 hours at a participation rate) and sort order. It is specific, but it does not name sibling tools like `exit_capacity`, so the distinction is not 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 description provides a clear list of example use cases ('what position limit should I set', 'which position is too big') and a caveat about interpreting limits as optimistic. However, it does not state when not to use this tool or recommend alternative tools.

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

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses the honesty requirement: 'these are prizes CONDITIONAL ON BEING FILLED. No fill probability is estimated anywhere in the response. Say so.' It also highlights a key behavioral condition: supplying `notional_usd` 'prices crossing as the real book walk and adds the best-venue-to-cross comparison per coin'. The API key requirement is also stated. This is exemplary transparency.

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 appropriately sized, front-loaded with the core purpose and use cases, then safety/behavioral notes, then parameter details. Every sentence carries informational weight, and the use of backticks for parameters aids readability. The honesty warning is concise and imperative. No padding or redundancy.

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

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

The description covers the tool's output (a table sorted by prize), conditional behavior, API key requirement, and default universe. An output schema exists (though not shown), so detailed return fields are not necessary. The only notable omission is the `side` parameter, which is left undocumented. This prevents full completeness.

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

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

Schema description coverage is 0%, so the description must compensate. It explains `coins`, `notional_usd`, and `limit` clearly: `coins` is 'optional comma-separated list (default: the liquid crypto perp universe by volume)', `notional_usd` controls a behavior, and `limit` is 'how many coins, max 40'. However, it entirely omits the `side` parameter, leaving its meaning and default ('buy') unexplained. This gap prevents a higher score.

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 'Universe-wide maker/taker table' and specifies the output: 'for each liquid crypto perp, the best venue to post on and the round-trip prize, sorted widest-first'. This is a specific verb ('post'), resource ('perp venues'), and scope ('universe-wide'), which clearly distinguishes it from siblings like post_value. Use cases like 'where is being passive worth the most' further clarify its unique role.

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

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

The description provides explicit use cases: 'Use for "where is being passive worth the most", "which coins should I be quoting rather than taking", "rank my book by spread capture"'. It also states a prerequisite: 'Requires an EnsoTrade Pro API key'. However, it does not explicitly state when not to use this tool or name alternatives (e.g., 'use post_value instead'), 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?

With no annotations provided, the description carries the full burden and excels. It discloses what the tool returns (spread, fees, posting value, round trip), the ranking behavior, the real-walk impact of notional_usd, API key requirements, and a major caveat that fill probability is not estimated. No contradictions exist.

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 longer than average, but every segment adds value: use cases, return details, measured statistics, caveats, and parameter guidance. It is front-loaded with the core concept and structured into clear functional blocks, though slightly dense.

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

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

Despite an output schema being present, the description enriches it with concrete return fields (spread, taker/maker fee, posting value, round trip) and real-world calibration data. It covers prerequisites (API key), limitations (no fill probability), and cross-tool guidance, making the tool complete for an agent.

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

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

Schema coverage is 0%, so the description must compensate. It explains 'coin' with an example ('sol'), and 'notional_usd' with behavioral detail ('price the crossing side as the real walk down the book'). 'side' is only implicitly covered via 'per side', but the default and usage are otherwise inferable from context.

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

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

The description opens with a specific, informative statement: 'What POSTING a resting order is worth versus CROSSING the spread, per venue, for a crypto perp.' It clearly distinguishes itself from sibling tools by defining its exact analytical role and explicitly references the related 'cross_vs_post' tool.

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?

Provides explicit use cases: 'should I use a limit order or market order', 'what does paying the spread cost me', 'which venue should I quote on'. It also names an alternative tool ('Also read cross_vs_post') and clarifies when not to interpret results as fill probabilities.

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

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

With no annotations provided, the description carries full burden. It explicitly discloses that it measures a live book, is not a prediction, assumes capital already on venues, ignores transfer costs, and requires a Pro API key. It also outlines return values (per-venue allocation, blended price, best single venue, savings in bp and USD), giving an accurate mental model of the tool's 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 well-structured and front-loaded with the core purpose, followed by use cases, return values, parameter details, and limitations. Every sentence adds value, and while detailed, it is concise enough to absorb quickly without redundancy.

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

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

Given the complexity of routing across six venues and the presence of an output schema, the description provides all necessary context: purpose, usage examples, parameter semantics, assumptions, and limitations. It is complete for an agent to correctly select and invoke the 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 provides no descriptions (0% coverage), but the tool description fully explains every parameter: coin as ticker, notional_usd as order size, side as buy/sell, venues as comma-separated subset with additional context about trading only on real venues. This fully compensates for the lack of schema 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 clearly states it finds the cheapest way to fill a crypto perp order across multiple venues, explains what it saves versus single best venue, and provides concrete use cases like 'how should I split this order'. This is a specific verb+resource that distinguishes it from siblings like market_snapshot or top_movers.

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 provides explicit use cases ('Use for...'), explains parameter semantics (e.g., optional venues subset for desks with limited accounts), and clearly states it is a measurement, not a prediction, with limitations (prices move, ignores transfer costs) and a prerequisite (Pro API key). This effectively tells the agent when and 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?

With no annotations provided, the description carries the full burden. It discloses server-side re-validation, the condition for saving ('validated'), privacy of saved strategies, and API key requirement. It does not mention response format or error handling, but covers core behavioral traits.

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 fairly long but contains necessary details. It front-loads the primary action, but could be more concise by combining some sentences. The structure is logical: action, validation behavior, privacy, parameters, requirements.

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 7 parameters (2 required), no enums, and an output schema, the description covers the tool's flow and key constraints. It does not detail the return value, but the presence of an output schema mitigates this. It explains re-validation, privacy, and parameters adequately for an agent to use the tool effectively.

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 the relationship between timeframe, horizon, and horizon_bars, and the purpose of label and hours. However, symbol and formula are only mentioned as 'as usual' without further detail, and enumeration options for timeframe are listed but not exhaustive.

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 that it saves a formula as a strategy only if it currently validates, and distinguishes itself from test_formula by re-running validation before saving. The verb 'save' and resource 'strategy' are specific and 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 explains when to use this tool (to save a validated formula), mentions the requirement of an EnsoTrade Pro API key, and cautions against trusting stale validation. It references sibling tool test_formula but does not explicitly contrast usage scenarios.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It reveals that the formula runs through a restricted expression evaluator, not eval(). It explains the 70/30 split, the validation criteria, the calculation of risk metrics, cost handling, and walk-forward analysis. It also warns about the difference between correlation validation and profitability.

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 lengthy but well-organized. It front-loads the main purpose and then breaks down details into logical sections (modes, output fields, costs, walk-forward). It uses code blocks for formula examples. While every sentence earns its place, a slight reduction in verbosity could improve conciseness, but the structure is clear.

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 complex tool with 8 parameters, no annotations, and an output schema (presence indicated), the description is exceptionally complete. It covers input constraints, output structure, validation logic, edge cases (minimum bars), cost calculation, and walk-forward analysis. It leaves no ambiguity for an AI agent to understand invocation and expected results.

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

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

The input schema has no parameter descriptions (0% coverage), so the description must compensate. It explains all parameters: formula syntax, timeframe options, horizon and horizon_bars (with dependence on timeframe), hours (max and minimum), fee_bp and slippage_bp (defaults and usage). It adds meaning with examples and constraints, fully compensating for the schema's lack of descriptions.

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

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

The description clearly states the tool's purpose: to invent a formula over EnsoTrade's data and test its predictive ability using a holdout split. It specifies the verb 'invent' and 'get back', the resource 'formula over data', and the output (validated correlations and risk metrics). The description distinguishes this from sibling tools like fetch_series or market_snapshot by focusing on formula testing.

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 clear usage guidance: iterate with different formulas, keep those that validate and survive costs. It mentions the requirement for an EnsoTrade Pro API key. It also explains the two modes (scalp vs. bar-based) and how to choose between horizon and horizon_bars. However, it does not explicitly state when not to use the tool, but the context is sufficient.

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

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

With no annotations, the description carries the full burden. It indicates real-time data ('right now') and global scope ('across the whole market'), which is helpful. However, it does not disclose details like sort order, data freshness, or any rate limits. The output schema may cover return values, but behavioral traits remain partially opaque.

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

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

The description is very concise (two sentences), front-loaded with the main purpose, and includes usage examples with no extraneous words. Every sentence earns its place.

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

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

For a simple tool with one optional parameter and an output schema, the description covers the core functionality. However, it lacks explanation of the 'limit' parameter and does not provide enough detail to fully guide an agent (e.g., default behavior, ordering). 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?

The description does not mention the 'limit' parameter at all. Since schema description coverage is 0% (no descriptions in schema), the description should compensate but fails. Although the parameter name is self-explanatory, the description adds no value beyond the schema's property definition.

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 returns the top gaining and losing crypto perpetuals, which is a specific verb+resource. The usage examples help distinguish from siblings by targeting queries about top movers, but it does not explicitly differentiate from other tools like market_snapshot or get_order_flow.

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

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

The description provides explicit use cases ('top crypto movers', 'biggest crypto gainers and losers today'), guiding the agent when to invoke it. However, it lacks negative guidance or when-not-to-use scenarios among the sibling tools.

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