AlphaYou Market Intelligence

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value beyond that by disclosing data staleness ("cached metrics") and scope limits ("available history only, not live positions"), which the agent cannot infer from 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 compact sentences, front-loaded with the primary use case followed by the exclusion. No filler or redundancy; every clause carries signal.

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-parameter, no-output-schema tool amid many Hyperliquid siblings, the description covers purpose, data freshness, and boundaries. It could be more complete by naming the live-position alternative, but nothing critical for 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?

Schema coverage is 0% and there is one required parameter, so the description must compensate. It clarifies the address must be a public Hyperliquid address, but adds no format or syntax detail beyond what the schema regex already enforces. Minimum-viable compensation.

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

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

States a specific verb (analyze) and resource (public Hyperliquid address) with a clear scope: historical performance and risk. It implicitly distinguishes itself from siblings by noting it is not live positions, though it does not name the specific sibling (e.g. get_hyperliquid_wallet_positions) it overlaps with.

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

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

"Use for historical performance and risk" plus "not live positions or owner identity" gives clear when-to-use and explicit exclusions. It stops short of naming the alternative tool an agent should pick for live positions, so it is strong but not maximally routed.

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 readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds value beyond that with the returned fields (analysis time, history length, losses, missing results) and an explicit disclaimer that no suitability or follower-return claims are made, which sets expectations about result interpretation.

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 the action and input constraint, followed by the return contents and scope caveat. 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?

With no output schema, the description must characterize the response, and it does so at a summary level. Combined with the read-only annotations and a single well-constrained parameter, an agent has enough to invoke it correctly; per-wallet output shape remains only broadly sketched.

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: it tells the agent the input is two to five wallets and that they must be distinct, a constraint the schema's minItems/maxItems does not enforce. It also clarifies these are public wallets, which the bare 0x-hex pattern does not convey.

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

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

States a specific verb (compare) and resource (two to five distinct public wallets), and the cardinality range implicitly separates it from the single-wallet sibling analyze_hyperliquid_wallet. It stops short of naming that sibling explicitly, so the differentiation requires an inference.

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

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

"Use one call" hints at batching several wallets together rather than calling analyze_hyperliquid_wallet repeatedly, but there is no explicit when-to-use condition or named alternative. Usage is 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 cover the safety profile (readOnly=true, destructive=false, openWorld=false), so the description is free to add the behavioral payload: that the response is a research-only limitation notice and that no wallet/money/order side effects occur. This is genuinely useful context beyond the annotations. It does not describe the response shape, but for a fixed refusal-style return that is a minor omission.

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

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

Three sentences, front-loaded with the trigger condition and followed by the limitation list. Every sentence carries information; the negative enumeration is long but earns its place by defining scope precisely.

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

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

With no output schema, the description does the necessary work of stating the return semantics ('supports research only'), and it fully frames the guardrail behavior. The remaining gap is the undocumented 'address' parameter, which an agent may need to populate without any guidance.

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 names the parameters. The request enum values (copy_trading, alerts) map loosely to the described triggers, but the required 'address' parameter with its 0x-pattern constraint is entirely unexplained in both schema and description. With zero coverage the description should have compensated and does not.

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

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

The description states a specific trigger and outcome: it is invoked for copy-trading or alerts requests and returns that only research is supported. This distinguishes it from the sibling hyperliquid/equity data tools, which all return analysis rather than a capability refusal. It is slightly indirect in phrasing (defined by trigger rather than by what it returns), but an agent can tell what it does.

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 an explicit when-to-use condition: 'requests to start copy trading or subscribe to alerts.' It also enumerates what the tool will NOT do (no wallet connection, funding, signing, ordering, copying, or scheduled tasks), which effectively steers the agent away from expecting those actions. No sibling alternative is named, but the negative list covers the practical guidance gap.

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

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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, but the description adds real behavioral context: the EDGAR source, the 365-day recency cap, newest-first ordering, and what each returned item contains (title, date, original SEC link). The closing caveat that a filing item number alone states no conclusion is useful framing, though auth demands and rate-limit behavior are not mentioned.

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 dense sentences, front-loaded with the use case before the return details and the exclusions. Every clause carries information, though the run-on first sentence packs several distinct disclosures together rather than structuring them.

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 return contract itself — record type, fields, ordering, time window and source — and also bounds expectations with exclusions. For a one-parameter read-only lookup, an agent has everything needed 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?

There is a single parameter ('ticker') with 0% schema description coverage; the schema only supplies a regex pattern. The description implies a US company ticker but never states the required uppercase format, symbol length, or how non-US or ambiguous tickers are handled, so it adds only partial meaning over the schema.

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

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

The description names a specific verb and resource (lists SEC 8-K/8-K/A filings) plus data source (SEC EDGAR), scope (US company, last 365 days), and ordering (newest first). It distinguishes itself from adjacent siblings such as get_company_earnings and get_stock_fundamentals by explicitly disclaiming news, sentiment, analyst opinion and a full filings archive.

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 when-to-use triggers (earnings-result disclosures, officer departures, material events) and an explicit when-not list (general stock news, article text, sentiment, analyst opinion, complete archive). It stops short of naming a specific sibling tool to use instead for those adjacent needs, so it falls just below the top band.

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 the safety profile (readOnlyHint, destructiveHint=false). The description adds genuine context beyond them: the data source ('validated stored SEC release facts') and the return cap ('up to eight reports with original release links and dates'). No auth or rate-limit detail, but the added provenance and cap are meaningful.

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 dense sentences with zero waste; the data scope and provenance come first and the exclusion list follows. Every clause earns its place.

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

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

With no output schema, the description carries the return burden and does so reasonably (count cap, release links, dates). For a single required ticker tool it is nearly complete, though parameter-level detail remains thin.

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 limit ceiling ('up to eight reports') but says nothing about the ticker pattern or what limit defaults to. Partial compensation only.

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

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

Specific verb+resource ('Research company-reported US earnings') with an enumerated field list (GAAP/adjusted EPS, revenue, margins, segments, guidance, capital allocation) that clearly separates it from siblings like get_company_disclosures and get_earnings_calendar.

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

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

Explicit exclusions ('No analyst estimates, beat/miss verdict, full transcript or current stock price') define the boundary and implicitly route the agent to other tools. It stops short of naming a specific alternative sibling, 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?

Annotations already declare readOnly/openWorld/non-destructive, so the bar is lower, and the description adds real substance: data provenance (stored SEC 8-K only), what is returned (filing links, extraction snippets, ingestion dates), and key limitations (incomplete coverage, dates can change, no provider fallback). That is meaningful disclosure beyond 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?

Four short sentences, front-loaded with the core action and scope, followed by provenance and caveats. Every sentence carries information and none is redundant 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?

With no output schema, the description steps in to say what is returned and flags coverage/volatility limitations, which is what an agent needs for a read-only lookup. The remaining gap is the undocumented limit parameter and the unclear relationship to get_company_earnings.

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 carry parameter meaning. It conveys the ticker mode and the 1-90 day range (days_ahead), and implies discovery mode when no ticker is given, but 'bounded discovery list' is vague about what bounds it, and the limit parameter (default 10, max 20) is entirely unaddressed.

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

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

States a specific verb+resource+scope: upcoming company-announced US earnings dates, sourced from SEC 8-K filings, within a 1-90 day window. This is far more specific than the title. However, it does not explicitly differentiate itself from the close sibling get_company_earnings, so an agent must infer which one to use.

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?

Implies two usage modes ('a ticker or a bounded discovery list') and sets expectations with caveats ('not a complete market calendar', 'missing dates are unknown'). But it never names an alternative tool or states when-not to use it, leaving the get_company_earnings vs get_earnings_calendar routing 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 cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint), so the bar is lower. The description still adds real behavioral context: values are computed only from matching verified SEC measurement periods, mismatched/unknown periods stay unknown, and each ratio retains source inputs and dates. That provenance and unknown-handling detail goes beyond what annotations 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?

Three sentences, front-loaded with purpose, then metric scope, then exclusions. The metric enumeration earns its length because it defines the tool's exact coverage, 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 usefully enumerates the returned ratios and their data provenance. It is nearly complete for a single-ticker read tool; the only gap is that it never explicitly positions itself against the fundamentals/earnings siblings that an agent might otherwise choose.

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

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

Only one parameter (ticker) and schema description coverage is 0%; the schema carries a pattern constraint but no textual meaning, and the description never mentions the ticker argument. Ticker semantics are largely self-evident, so the schema's format pattern plus common sense keeps this at a baseline 3, but the description contributes nothing on 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 names a specific verb ('Inspect') and a precise resource ('profitability and balance-sheet ratios'), then enumerates the exact metrics (gross, operating, net, cash-flow margins, liabilities/assets, etc.). The closing negative scope ('No stock price, valuation multiple, analyst estimate, score or buy verdict') further sharpens the boundary against siblings like get_stock_fundamentals and get_company_earnings.

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

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

Usage is implied rather than stated: the negative scope hints that valuation/estimates live elsewhere, but the description never explicitly says when to pick this tool over get_stock_fundamentals or get_company_earnings. There are no stated prerequisites or exclusions phrased as 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 declare readOnly/openWorld/non-destructive, so the bar is low, and the description adds real value: the data is 'stored' and 'weekly reported positions lag trading,' disclosing staleness. It also notes TFF and disaggregated categories 'remain distinct,' a nuance not in 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?

Front-loaded with verb+resource, then progressive detail on scope, contents, and caveats. Dense but every sentence carries information; no wasted 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 usefully describes return contents ('dated category long/short/net contract counts and open interest') and limits. Combined with the latency and category caveats, it is close to sufficient 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 coverage is 0%, so the description must carry the load; it does so reasonably by enumerating all four contract enum values and signaling the count nature of reports via 'up to eight stored reports.' It still omits the default value and what the count selects (e.g., most recent).

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

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

States a specific verb and resource (read stored CFTC futures-only reports) and enumerates the four supported contracts with their meanings. It distinguishes itself from sibling tools by scope, but never names an alternative sibling to route against.

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 clear exclusions — 'no wallet identities, real-time flows, options chain or stock shares' — which effectively tell the agent when this tool is not the right choice. It does not, however, name which sibling to use instead for those 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?

Annotations already declare readOnlyHint/destructiveHint/openWorldHint, so the safety profile is covered. The description adds genuinely non-obvious behavior: oldest-first single-page pagination with since/next_cursor continuation, a $1M default notional floor, and the caveat that watcher uptime is unknown. It omits auth/permission or rate-limit behavior, keeping it below 5.

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

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

Front-loaded with 'Use for...' and packed with high-value facts in five compact sentences. The dense notional/pagination clarifications are each doing work, though the sentence order (uptime caveat last) is slightly less scannable than it could be.

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

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

With 8 parameters, 0 required, no output schema and 13% schema coverage, the description covers pagination, the notional floor and the data-reliability caveat, which are the highest-risk gaps. But it leaves the event enum values, coin format and address filter unexplained, so an agent still lacks a complete picture for calling all parameters 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 13%, so the description must carry parameter meaning. It clarifies hours (1-168), min_position_notional_usd (default $1M, pass 0, and the important 'position size not incremental trade amount' distinction) and since's continuation semantics, but coin, event, limit, cursor and address are left entirely to the schema. Partial compensation warrants a 3.

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 resource and scope: observed position changes over 1-168 hours in the 'watcher cohort'. It also distinguishes itself from adjacent concepts by stating it is 'not alerts or an exhaustive live trade feed'. It does not name the specific sibling tools (e.g. get_hyperliquid_positioning) it differs from, 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?

It opens with an explicit 'Use for...' context and adds clear exclusions ('Not alerts or an exhaustive live trade feed'), which tells the agent when this tool is the wrong choice. However, it never names an alternative sibling to route to, so the when-to-use guidance is strong but not fully directional.

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 the safety profile (readOnlyHint, destructiveHint=false, openWorldHint), so the bar is lower. The description adds genuinely useful behavioral context beyond them: it discloses the temporal caveat that only retrieval time is returned and the exchange observation time is unknown, and it sets expectations with "Not a prediction."

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

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

Three short sentences, led by the "Use for..." trigger, with each sentence earning its place (capability list, stock-quote disambiguation, temporal caveat/expectation). The "Not a prediction" fragment is terse but purposeful; 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 does double duty and reasonably lists the returned fields plus the retrieval-time caveat for a simple single-parameter read tool. The main remaining hole is the asset-identifier format and behavior for an unknown asset, neither of which is 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?

There is one parameter (asset) with 0% schema description coverage, so the description carries the full burden. It never explains the asset identifier format, examples, casing, or naming convention, and the existence of a resolve_hyperliquid_market sibling suggests asset resolution is non-trivial. The only hint is the implied 'market' phrasing.

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 gives a specific resource and enumerates the exact fields returned (mark price, 24h change, funding, open interest, volume), and explicitly contrasts it with a US stock quote to separate it from the financial-data siblings. It does not explicitly route the agent to the adjacent Hyperliquid siblings (e.g. resolve_hyperliquid_market), so sibling differentiation is only partial.

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

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

"Use for a Hyperliquid market..." supplies a clear trigger condition, and "not a US stock quote" acts as a mild exclusion against the stock tool family. However, there is no guidance on when to prefer the many nearby Hyperliquid siblings, nor any prerequisite or when-not statement beyond the stock contrast.

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 and destructiveHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral caveat beyond that: 'Newest row update is not whole-cohort freshness' warns the agent the timestamp is not a cohort-wide freshness signal. It does not cover latency, cohort definition, or return shape.

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

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

Three short sentences, no filler, with the primary use case front-loaded ahead of the caveats. The freshness warning is compact to the point of being slightly cryptic, which costs a point but keeps the entry token-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 one-parameter read tool with annotations and no output schema, the description states what is returned (notionals and counts), the population (qualified cohort), the input format, and a freshness caveat. The main omission is that 'qualified cohort' is never defined, which could change how an agent interprets the numbers.

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 carries the full parameter burden, and it does so well: it says the asset must be an 'exact case-sensitive asset' and gives concrete examples ('BTC or xyz:NVDA') that illustrate the namespace-prefixed form allowed by the pattern. It does not explain the pattern's 'k' prefix variant or the max length constraint.

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

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

The description names the exact resource and metrics returned (long/short notionals and counts in the qualified cohort for a given asset) rather than restating the tool name. It also scopes what it is not ('total exchange positioning or a price prediction'), which helps separate it from market-state siblings. It stops short of naming a specific alternative tool for those other needs.

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

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

'Use for long/short notionals and counts...' gives a clear trigger for invoking the tool, and the negative scope statements rule out two misuses. However, it never names a sibling tool to use instead (e.g. get_futures_positioning or get_hyperliquid_market_state), so routing between near-identical positioning tools is left to inference.

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

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

Annotations already cover read-only, non-destructive, open-world, so the bar is lower; the description adds real behavioral context beyond them: default venue is native only, named assets like Nvidia are resolved to a venue, and empty native results are not exhaustive. Return format/pagination are still unstated.

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 sentences with no waste; the primary purpose is front-loaded, followed by parameter behavior and then the interpretation caveat. Every sentence carries distinct information.

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

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

For a 3-param read tool with no output schema and 0% schema coverage, the description supplies the key resolution semantics and a meaningful caveat about empty results. It is nearly complete, missing only explicit guidance on the dex/asset interaction and what a populated response looks like.

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 carry the load, and it does: it explains the asset parameter (optional, named markets resolved to a venue) and the venue default behind the dex parameter. It never explicitly ties these to the parameter names, but the intent is recoverable.

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

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

States a specific verb+resource: positions for one public Hyperliquid wallet on one perpetual venue. Implicitly scopes to a single wallet (vs. the plural sibling get_hyperliquid_wallets_positions) but never names that near-identical sibling, leaving some disambiguation to inference.

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

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

"Use for positions of one public Hyperliquid wallet on one perpetual venue" gives clear usage context, and the caveat that an empty native result does not establish absence across venues is genuinely actionable. No explicit alternatives or exclusions are named, so it stops short of 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 declare read-only, open-world, non-destructive. The description adds real behavioral context beyond that: single-venue scope, bounded upstream concurrency, and per-wallet failure reporting. It stops short of describing return format or throttling specifics.

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 tight sentences, front-loaded with the usage instruction, each adding distinct information (scope, concurrency/failure behavior, optional param). 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?

For a batch read tool with no output schema, it covers scope, venue limitation, and partial-failure handling while annotations carry the safety profile. The only meaningful gap is that the dex parameter is never named or explained.

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 carry parameter meaning. It explains the optional asset for named markets and the two-to-five wallet bound, and 'one venue' hints at the dex parameter, but dex and the address format are never explicitly documented.

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

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

States a specific verb and resource (positions of two to five wallets in one batch call) and its batch scope clearly distinguishes it from the singular wallet-positions sibling. It does not explicitly name the alternative tool, but the 2-5 wallet bound makes the purpose 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?

'Use for ... for example after a ranking' gives a concrete workflow trigger for selecting this tool. It provides clear usage context but names no exclusions or the single-wallet sibling an agent should use instead for one address.

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/destructiveHint=false and openWorldHint=true, so safety is covered. The description adds genuine context beyond them by disclosing that data is 'stored' (not live) and that returns carry per-series units and observation dates, though it omits refresh cadence or rate limits.

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

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

Three sentences, front-loaded with the coverage enumeration, then return format, then exclusions. 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?

For a zero-parameter, read-only tool with no output schema, the description adequately explains what is returned (per-series units and observation dates) and what is not included. It could still mention data freshness/update behavior, but nothing critical to invocation 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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter-level meaning is required here.

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

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

States a specific verb (Inspect) and a well-scoped resource (stored US government macro observations), then enumerates the exact series covered. An agent can immediately tell this apart from siblings like get_futures_positioning or get_smart_money, which cover different data domains.

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?

Clear context is given via the negative scoping: 'No proprietary volatility, credit spreads, consumer surveys, stock breadth or AlphaYou regime score' and 'Not live economic releases or a forecast.' This tells the agent when NOT to use it, but it names no alternative tool to route to for the excluded data, leaving that 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?

It discloses a lot of behavioral context: bounded coverage, a three-row cap applied after filtering, grouped identical rows, matchingStoredRows not being a transaction count, source links per row, and the semantic nature of each category (fund changes are reported holdings, influencer posts are commentary, trader positions are derivatives, government awards lack direction). It never states auth or rate-limit requirements, and the read-only/open-world profile is already covered by annotations, so this lands above baseline without being exhaustive.

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?

Roughly seven packed sentences with no filler, and the most decision-relevant facts (what it covers, filter semantics, ticker omission behavior) come first. Later sentences are telegraphic to the point of terseness (e.g., 'Category congress covers politicians'), but nothing is wasted.

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

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

With no output schema, the description must describe returns, and it does: bounded discovery preview vs ticker-scoped research, three-row cap, per-row source links, grouped identical rows, and the caveat about matchingStoredRows. For a four-parameter read tool this is complete enough to call correctly without opening anything else.

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 carry the meaning: it explains activity values (buy/adding/accumulating, sell/reducing, all), maps 'congress' to politicians, gives example actor strings (Pelosi, Berkshire), and explains ticker omission vs presence. However 'funds', 'insiders', 'gov-contracts', 'influencers', 'top-traders' enum values and the ticker pattern itself are not explained, so the coverage is partial.

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

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

The description names a concrete resource (smart-money activity: buys, sells, holdings, statements) and enumerates the covered actor classes (Congress, insiders, funds, influencers, top traders). It implicitly differentiates from siblings by ruling out 'market-wide convergence ranking' (pointing away from get_smart_money_overlap), though it never names the alternative directly and the opening verb is buried in a long enumeration.

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 explicit conditional behavior: omitting the ticker yields a discovery preview, supplying one yields security research, and activity/category filters narrow results before the three-row cap. What's missing is an explicit 'use X instead when...' pointer to a named sibling, leaving the convergence-ranking exclusion as the only routing hint.

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 (readOnlyHint, destructiveHint=false, openWorldHint), so the bar is lower, and the description still adds real behavioral substance: the bounded six-preview scope, the returned row shape (dated rows plus per-category purchase/sale, holdings-change, commentary and derivative directions), and the non-obvious rule that awards are non-directional. It omits auth/permission requirements and any latency or freshness caveats, keeping it short of a 5.

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

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

Front-loaded with the core action and return shape before the disclaimers, which is the right ordering. The closing negation list runs five items long, and 'Awards are non-directional' is terse to the point of opacity, but no sentence is pure padding.

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 correctly carries the burden of describing what comes back (original dated rows plus per-category directions). For a single-parameter descriptive read tool, that plus the scope and exclusions is nearly everything an agent needs; only the ticker-format detail is left entirely to the regex.

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 single property only carries a regex pattern, so the description must supply the meaning. 'For one US stock' usefully constrains the ticker to a US equity symbol, but it adds nothing about format, case, or exchange-suffix behavior already implied by the pattern. Baseline 3 with one param and thin 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?

States a specific verb (inspect) and resource (agreement/conflict across the six bounded AlphaYou smart money previews) scoped to one US stock. It explicitly fences itself off from sibling-adjacent concepts (confluence scanner, distinct-actor count, scored signal), so an agent can distinguish it from get_smart_money and the other AlphaYou tools without opening a 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?

The scope statement ('for one US stock') and the negative list ('not a market-wide confluence scanner... not a saved alert') make the intended use case clear and rule out plausible misuses. However, it never names an alternative tool (e.g. get_smart_money) or states the condition that should route the agent there, so routing is left to inference.

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

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

With annotations covering safety (readOnly, openWorld, non-destructive), the description layers on substantial behavioral context: concepts may come from different filings, a period link does not verify every value, each metric has its own verified start/end dates, and durations may remain unknown. It also discloses that annual/interim periods are separate and standalone quarters are not inferred, which materially shapes how an agent should interpret results.

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 most important scope statement is front-loaded in sentence one, and each subsequent sentence carries genuine semantic content. It is dense and longer than typical, but nearly every clause earns its place; the period-duration passages are slightly repetitive.

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

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

No output schema exists, so the description must explain return semantics, and it does: period dates, per-row filing links, per-metric date ranges, and unknown durations. For a single-parameter read tool this covers everything an agent needs to call and interpret it correctly.

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

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

Only one parameter (ticker) with 0% schema description coverage, so the schema carries the pattern but no semantics. The description implies the ticker must be a US company identifier, which adds some meaning, but never addresses ticker format, exchange suffixes, or case expectations beyond what the pattern enforces.

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 first sentence names a specific verb-resource pairing ('Reads stored SEC Company Facts') and enumerates the exact data domains covered (revenue, earnings, assets, debt, cash flows, historical statements). The closing exclusions (no prices, valuation ratios, analyst forecasts, buy verdict) further sharpen its identity against price/forecast-oriented siblings like get_financial_quality or get_company_earnings.

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

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

'Use this for a US company revenue...' gives clear positive trigger conditions, and the final sentence supplies explicit negative scope (no prices, valuation ratios, forecasts, verdicts). It stops short of naming a specific alternative sibling to use instead, so it is strong but not a full routing directive.

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 and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-annotation context: it returns 'alternatives, ambiguity and coverage' (signaling graceful handling of non-unique or missing symbols) and the domain caveat 'A perpetual contract is not the underlying stock', which prevents an equity/perp conflation error.

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

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

Three short sentences, front-loaded with the trigger and followed by return content and one caveat; nothing is padded or redundant. Slightly telegraphic ('ambiguity and coverage' without elaboration) keeps it just under the top mark.

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

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

For a one-parameter resolver with no output schema, the description covers what it does, what kinds of input it accepts, the shape of the result, and the key semantic pitfall. It lacks failure-mode detail (what happens on no match) and cross-tool routing, but is adequate for correct invocation.

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

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

Schema description coverage is 0%, so the description must carry the input burden, and it partly does: the examples reveal that 'asset' accepts a company name (Nvidia), a ticker (NVDA), a coin (ETH/Bitcoin), or a raw venue symbol. It does not state length limits, case sensitivity, or single-asset-only constraints, so the compensation is helpful but incomplete.

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 specific verb 'resolve' plus the named resource ('Hyperliquid metadata') and concrete input examples (Nvidia, NVDA, Bitcoin, ETH, venue symbol) make the tool's job immediately clear; it is the only resolver among 21 sibling fetch/analysis tools. It stops short of a 5 because it never explicitly contrasts itself with look-alike siblings such as get_hyperliquid_market_state.

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 opening 'Use to resolve ...' supplies an implicit trigger: you have an identifier that needs mapping to a Hyperliquid market. However, with ~20 Hyperliquid-related siblings, there is no when-not-to-use, no named alternative, and no prerequisite guidance, so the routing burden remains on 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 the safety profile (readOnly, non-destructive, openWorld), so the bar is lower; the description still adds real behavioral detail by disclosing pagination behavior – a hard cap of ten rows per page and a next_offset cursor when more exist. It does not cover rate limits, auth requirements, or what fields a row contains, but the pagination disclosure is genuine added value.

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 tightly packed sentences with no filler; the primary use case is front-loaded, followed by return behavior, then filters, then exclusions. Every sentence carries distinct information an agent needs.

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 optional parameters and no output schema, the description supplies the scoping, filtering, sorting, and pagination context needed to invoke it correctly. It omits any indication of what a returned trader row looks like and what 'qualified cohort' means, which is the main remaining 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?

Schema description coverage is 0%, so the description must carry the load, and it does substantially: it clarifies that asset is an exact match, that leverage_tier is a filter, that sorting is between score and Sharpe, and that limit/offset drive ten-row pagination. It does not name the limit default (3) or reconcile the schema's 'offset' with its own 'next_offset' cursor terminology, leaving a small 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?

States a specific verb and resource: a historical score or Sharpe ranking of the qualified trader cohort. It also draws a boundary with three named exclusions (market-wide ranking, 30-day PnL sort, personalized recommendation), which helps separate it from siblings, though it never names the actual sibling tools that cover those cases.

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 opening clause tells the agent when to reach for this tool, and the closing sentence enumerates three things it is NOT for, which is clear exclusion guidance. It stops short of pointing to the alternative tool for those excluded cases, so the routing is implied rather than explicit.

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