Tape — Hyperliquid Analytics

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

The description adds the behavioral disclosure that the result 'carries provenance,' which is beyond what the annotations provide (readOnlyHint, idempotentHint, destructiveHint). It also reinforces the read-only nature, though that duplicates the annotation. Given annotations already cover the main safety profile, the extra provenance note earns a solid score.

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 with zero fluff. The core purpose is front-loaded, the usage guidance follows immediately, and the provenance note is appended without redundancy. 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 bundle tool with no required parameters and no output schema, the description adequately explains what it returns (the listed components), when to use it, and a behavioral note about provenance. It doesn't describe the return format or error conditions, but these are not critical for a read-only, idempotent bundle. Minor gaps exist, but overall it's sufficient.

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

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

The input schema already provides 100% coverage for the single parameter 'feed' with its enum and description. The description does not mention the parameter at all, adding no extra meaning. Since schema coverage is complete, the baseline of 3 is appropriate.

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

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

The description clearly states the tool is a unified read-only bundle that aggregates market consensus, pulse, live signals, funding extremes, and the live alert queue. It uses a specific verb and resource, and distinguishes itself from sibling tools by naming the narrower alternatives. No ambiguity about what the tool 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?

The description explicitly advises 'Prefer the narrower tools when you need one part,' which provides clear guidance on when not to use this bundle and implies using it when multiple analytics are needed. It names the category of alternatives ('narrower tools') but doesn't list them individually, so it's slightly less explicit than it could be.

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, idempotent, openWorld and non-destructive, so the safety profile is covered; the description goes further by disclosing that rows are sampled rather than complete, that labels are mechanical rule-derived values under a linked disclosure, and that the payload carries provenance (endpoint and fetch time). That is meaningful context an agent cannot get from the schema. It stops short of describing rate limits, sorting/tiebreak behavior, or what an empty result means.

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?

Purpose is front-loaded in the first sentence, followed by the differentiating caveat, then the label semantics. The long clause stack about labels and the prohibitive disclaimer is dense, but each part earns its place by preventing a specific misuse (restating labels as skill judgements).

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 burden of explaining return shape, and it does describe rows, the labels object and its three components, and a provenance field. The link to the label rules covers the recursive detail economically. What is thin is the actual row field list (rank, address, raw numbers) which is only revealed in the response_format parameter text.

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

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

Schema coverage is 100% and every parameter has an inline description with defaults and enums, so the baseline is 3. The prose contributes only tangentially — 'the four published windows' and the metric list loosely echo the enum values — and adds no syntax, interaction, or format guidance beyond the schema.

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

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

The first sentence names the resource (Hyperliquid wallets), the ranking dimensions (PnL, ROI, volume, account value) and the scoping (sampled, across time windows). It also pre-empts a likely confusion by stating it is not the official leaderboard. It never names a sibling, so an agent must infer the split with tape_wallet_analysis or tape_markets_radar 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?

Usage is implied by the noun 'leaderboard' plus the sampling caveat, but there is no explicit when-to-use, when-not-to-use, or named alternative among the ten siblings. The 'sampled' framing hints this is not a complete universe, yet the description never tells the agent which tool to reach for when it needs exhaustive or single-wallet coverage.

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

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

Annotations already declare read-only, idempotent, open-world, and non-destructive behavior; the description adds substantial behavioral context by disclosing that CONCISE returns only the densest levels in a few hundred tokens, DETAILED returns the full grid, and the result carries provenance. No contradiction with annotations.

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

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

Two sentences deliver the core concept, the non-forecast boundary, both response modes and their sizes, and provenance. The information is front-loaded and every sentence earns its place; there is no repetition of schema or annotation fields.

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 zero required parameters, no output schema, and a moderate tool, the description still supplies enough to invoke correctly: supported coins, timeframe semantics via schema, response_format behavior, and the meaning of returned data. The main unstated details are the exact JSON shape, which is not strictly necessary for a correct call.

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

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

The schema already documents coin and timeframe defaults/options; the description compensates for the undocumented response_format parameter by explaining CONCISE (default) vs DETAILED and their output sizes. It also restates supported coins, adding practical context beyond the bare enum. It does not add further meaning to timeframe, but the schema covers that adequately.

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 and resource: it reports observed liquidation price levels for BTC, ETH, SOL, or HYPE, and specifies the output's content (price buckets, realized liquidations, share of open interest observed). The explicit 'Not a forecast' caveat further sharpens what the tool is and is not. Though it doesn't name a sibling tool, the description is detailed enough to distinguish it from a raw liquidation feed.

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 clearly implies the use case—requesting liquidation heatmap/coverage for major coins over a chosen timeframe—and adds an explicit when-not in 'Not a forecast.' It also explains when to choose CONCISE vs DETAILED. However, it never names an alternative such as tape_liquidations or says when to prefer that sibling over this heatmap.

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

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description goes further by disclosing a critical sampling trait — data is recovered from liquidation counterparty fills, is a sample rather than a census, and the payload states its coverage. This provenance detail is meaningful beyond structured annotations.

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

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

The description is front-loaded with purpose, then gives a caveat, then usage specifics, and closes with provenance. It is compact and every sentence provides useful information, though 'Result carries provenance' slightly overlaps with 'the payload states its coverage.'

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 still enumerates the key return contents: liquidation events, aggregate totals, largest event, and top markets. Combined with schema descriptions for since and minNotional, and annotations for safety, an agent has enough to select and call the tool correctly.

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

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

Schema coverage is 60%, so the description must compensate. It adds the default limit of 50, clarifies the filterable dimensions (coins, side, minNotional), and frames limit as a cap. It does not add much for 'since', but the schema already documents that parameter sufficiently.

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 opening phrase 'Live liquidation feed on Hyperliquid perps' plus the enumerated outputs (side, size, price, wallet, 1h/4h/24h totals, largest event, top markets) precisely identifies the tool's function and differentiates it from siblings like tape_liquidation_heatmap or tape_live_alerts.

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 concrete invocation guidance: filter by coins, side, or minNotional, and cap with a default limit of 50. It also warns that results are a sample, not a census. However, it does not explicitly state when to choose this tool over its siblings, so the guidance is clear but lacks 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety and side-effect behavior. The description adds 'Result carries provenance,' which is a useful output trait not captured in annotations, but it does not disclose other behaviors such as real-time latency, pagination, or rate limits. Since annotations carry most of the burden, this is adequate but not rich.

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, front-loaded with the resource and alert types, then covering filtering and output. Every clause carries information, with no fluff or repetition. It is efficient and well-structured.

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

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

With no output schema, the description mentions provenance but does not explain the result shape, severity labels, or how the 'plain-English read' is formatted. Given the tool's moderate complexity (three optional parameters) and rich annotations, the description is functional but leaves gaps about the return structure that an agent might need for correct interpretation.

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

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

Schema description coverage is 100%, so each parameter already has an explanation. The description only restates the filtering concept ('Filter by coins or severity, cap with limit') without adding syntax, defaults, or format details beyond the schema. This meets the baseline for high coverage, with minimal added value.

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

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

The description identifies a specific resource (live alert queue) and lists the types of alerts (funding extremes, signal fires, consensus flips), which clarifies what the tool returns. It doesn't explicitly name sibling tools for differentiation, but the term 'live alerts' distinguishes it from analytics, leaderboards, and other listed tools. The verb is implied (get/list), but the intent is clear.

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

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

The description mentions filtering by coins or severity and capping with limit, which is parameter usage, but provides no guidance on when to use this tool versus alternatives like tape_market_signals or tape_market_pulse. No when-not-to-use or alternative routing is given, leaving the agent to infer the appropriate context.

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

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful context about the result carrying provenance and the live nature of the data, which goes beyond the structured annotation fields without contradicting them.

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

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

The description is extremely concise, using two sentences to enumerate what the tool returns. It is front-loaded with the core value proposition and every phrase adds meaningful content with 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?

For a no-parameter, read-only snapshot tool, the description is complete. It lists the major output categories, mentions provenance, and combined with the annotations gives an agent everything needed to call and interpret the tool correctly. No output schema exists, but the description sufficiently covers the return content.

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 are no parameter meanings to clarify. The schema already reflects this, and the description does not need to compensate for any parameter documentation gaps.

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: providing key live Hyperliquid metrics such as BTC/ETH marks, volume, open interest, funding, a sentiment score, and top wallets by PnL. It is specific about the resource and content, though it does not explicitly distinguish itself from sibling tools like tape_market_signals or tape_markets_radar.

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

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

The description gives no guidance on when to use this tool versus its many siblings. It does not mention alternatives, exclusions, or situational fit, leaving an agent to infer that this is a general market pulse snapshot.

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

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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real context: results are mechanical screens, not advice, and each result carries provenance. It doesn't disclose refresh cadence or how 'strength' is scaled, 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 what the tool does and which signals it covers; every sentence is short. The three-sentence disclaimer tail ('not recommendations', 'do not trade on them alone') is repetitious and could be compressed into one clause.

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 correctly takes on the return-value burden by summarizing strength, supporting numbers, consensus, and provenance. It omits any detail about ordering, snapshot staleness, or result volume beyond the limit cap, which leaves a small gap for an agent interpreting output.

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

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

Schema coverage is 67% — bias has an enum and coins has a description, while limit has none. The description's 'cap with limit' slightly clarifies limit's role, but adds no syntax, defaults, or units beyond the schema. Baseline 3 is appropriate.

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

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

Names a concrete resource (Hyperliquid perps), the three signal families it screens for (funding carry, premium dislocation, momentum), and the shape of the result (strength, supporting numbers, overall long/short consensus). An agent can tell this apart from siblings like tape_market_pulse or tape_markets_radar by the rules-based setup framing.

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 filtering intent ('Filter by coins or bias, cap with limit') and a clear interpretive boundary ('informational only... not recommendations to buy or sell'), but never says when to pick this over the ten sibling tape_* tools or what conditions make it the right choice. Usage is implied rather than contrasted 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?

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds meaningful behavior beyond that: default 25 most extreme funding APR rows, concise fields, ~13k token scale warning, and provenance metadata in the result. It does not discuss freshness or failure modes, but for this read-only radar tool the extra context is solid.

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 tight sentences with no fluff. The main action and default behavior lead, and the scale/provenance warnings follow naturally. Every sentence contributes useful operational information.

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

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

The description covers purpose, defaults, scope, caveats, and result provenance, which is enough for an agent to call it correctly without an output schema. It could add a bit more about row semantics for non-default sorts, but the schema already enumerates the sort keys and response formats.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds extra decision-supporting meaning: the default is 25 concise rows, asking for optional params should be deliberate because of the ~13k token scale, and DETAILED maps to a heavier result. This goes beyond simply restating schema fields.

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

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

The description states a specific action and resource: 'Rank live Hyperliquid perpetual markets' by multiple explicit metrics. It also clarifies coverage ('every listed perp including HIP-3 builder markets'), which distinguishes it from sibling tools focused on analytics, alerts, or wallet 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?

It gives clear situational context: use it when a ranked market view is needed scan. It also explains the default behavior and cautions when to ask for optional parameters ('Ask for limit, sort, coins or DETAILED only when you need them'). It does not explicitly name alternatives or list when-not conditions, slightly limiting the score.

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

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

Annotations already establish readOnly, non-destructive, and idempotent behavior. The description adds genuinely useful context beyond the annotations: it mentions the provenance field with source-specific as-of datesassword, explains that it renders as a chart in MCP Apps, and notes the educational-only nature.

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

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

The description is dense but well structured: core content first, then caveats, provenance, and rendering behavior. It is slightly long due to the enumeration of rates and auctions, but every clause adds information an agent would want before invoking the tool.

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

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

For a no-input, read-only information tool, the description covers the data content, sources, provenance, and client-side rendering behavior. There is no output schema to reference, so a brief note about the return shape or data frequency would make it fully complete, but nothing critical 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?

This tool has zero parametersNotifications, so the schema is trivially complete. The baseline for a no-parameter tool is 4, and the description adds no conflicting or unnecessary parameter information.

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

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

The description clearly identifies the resource as the US Treasury par yield curve and enumerates its key components (forwards, NY Fed rates, auctions, AI read). Although it lacks an explicit action verb like 'retrieves' or 'provides', the domain and output are unmistakable and distinct from the general tape analytics 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 gives no explicit guidance on when to use this tool versus alternatives like tape_market_pulse or tape_analytics. The 'Educational only' caveat is a limitation, not a selection criterion, so an agent must infer the intended use solely from the resource name and content.

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

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

Annotations already cover readOnly, idempotent, openWorld, and non-destructive, so the safety profile is settled. The description adds genuinely new behavioral context the annotations cannot express: per-call billing, that per-call tools do not renew, that stopping calls cancels, and that output is informational only. It does not discuss rate limits or failure modes, so it is strong but not 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?

Purpose and report contents are front-loaded, then pricing, then the routing hint — a sensible order. The billing block ('Billing period is per call. Per-call tools do not renew. Stop calling to cancel.') is three short sentences saying largely the same thing, which is mild redundancy rather than waste.

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 report's contents (equity, positions, leverage, liquidation distance, history), so an agent knows what comes back. Given only two params and full annotation coverage, that is nearly enough; a note on report freshness or latency would close the 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 100%, so both parameters are already fully documented, and the voice enum's price text in the schema duplicates the description's pricing sentences. The description adds no new per-parameter meaning beyond restating the gemini/grok price differential. Baseline 3 is appropriate when the schema does the work.

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 ('Risk and track-record report for one public Hyperliquid wallet') and enumerates the report contents: equity, open positions, effective leverage, distance to liquidation, and history. The scope (one wallet, public chain data) distinguishes it cleanly from the sibling market-wide tools like tape_leaderboard and tape_whale_prints.

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 after tape_leaderboard or tape_whale_prints hands you an address' gives an explicit trigger and names the sibling tools that feed it, which is exactly the routing an agent needs. It stops short of stating when *not* to call it (e.g. no address on hand), so it isn't a full when/when-not/alternatives treatment.

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 indicate this is read-only, idempotent, and non-destructive. The description adds meaningful behavior beyond annotations: the 36-hour recency window, the $100k threshold, the default/max limit values, and provenance of 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?

Three focused sentences deliver the core data scope, time window, filters, and a key output characteristic. Every sentence adds information, with the most important definition front-loaded.

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

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

For a read-only data tool with three optional parameters and no output schema, the description provides enough context: what data is returned, time window, threshold, filters, and result provenance. It could be slightly more explicit about the response shape, but this is not a major gap.

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

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

The schema covers coins and minNotional, but not the limit default or its semantic meaning. The description adds the default limit of 20, the max of 200, and clarifies that minNotional filters the feed floor at 100000. This compensates for the schema's partial coverage.

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

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

Description clearly defines the tool's output: recent fills of $100k or more from top Hyperliquid wallets over the last 36 hours, including net buy/sell flow and top markets. It is specific enough to distinguish from sibling tools that cover broader analytics, liquidations, or live alerts.

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 implicitly tells the agent when to use this tool: when whale-sized recent fills, net flow, or market concentration from top wallets are relevant. It does not explicitly name alternatives or exclusions, but the scope and filter options are clear.

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