solenrich

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

No annotations are provided, so the description carries the full burden. It documents that the tool is proprietary and derived from SolEnrich's own query stream, and it discloses the window semantics (acceleration compares three consecutive windows). However, it doesn't explain what the output format looks like, whether results include divergence classification per token, or how 'attention' is measured/aggregated beyond query velocity.

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 compact, front-loaded with the core purpose first, and efficiently packs the divergence classes, data source, and window sizes. It's slightly dense with jargon (early_signal, distribution_risk, fading) but each sentence earns its place. The parentheses definitions help readability.

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

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

Given the absence of annotations and output schema, the description provides a reasonable ground floor: it defines the core scoring concept, divergence taxonomy, and window behavior. However, for a ranked-momentum tool with nuanced signal classes, the description doesn't clarify what the returned data structure contains (per-token class labels? raw values?) or how an agent should interpret/combine the divergence classes. It's adequate but leaves interpretive gaps.

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

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

Schema coverage is 100%, and the description adds value by explaining the window parameter semantics ('acceleration compares three consecutive windows of this size'). The description also mentions divergences and windows (1h, 6h, 24h) which aligns with the schema. However, no additional meaning is added for the limit parameter beyond its schema description, which is adequate given full schema coverage.

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

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

The description clearly states the tool ranks tokens by acceleration of agent attention overlaid with price change, with specific divergence classes. It identifies the resource (tokens) and the action (rank by momentum). It doesn't explicitly distinguish from siblings, though the proprietary 'SolEnrich query stream' angle does differentiate its data source from other market tools.

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

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

The description explains the divergence classes and the underlying mechanism (agents researching before market moves), which implies when it's useful. However, it doesn't explicitly state when to use this vs sibling tools like token_trend, trending_signals, or consensus_signal, nor does it give exclusion criteria. The proprietary/unique-signal framing gives context but not explicit alternatives.

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

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

No annotations are provided, so the description carries the full burden. It discloses that results are returned in parallel, which is a useful behavioral trait, but it omits details on side effects, safety, error handling, or authentication. This is minimal but not absent transparency.

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

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

The description is a single, front-loaded sentence with no wasted words. It conveys the core operation, the batch scope, the limit, and the return behavior efficiently.

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

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

For a tool with no output schema and no annotations, the description covers the essential aspects: range, types, and parallel results. It does not explain the concept of 'enrich' results or the depth parameter, but the schema handles the latter. Overall, it is adequately complete for a simple batch operation.

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?

All three parameters have descriptions in the schema (100% coverage), so the baseline is 3. The description reinforces the 1-25 limit for addresses but adds no new parameter-level meaning beyond what the schema already provides.

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

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

The description clearly states the tool's function: enriching multiple wallets/tokens in a single call. The word 'batch' and 'multiple' distinguish it from single-item enrichment tools like enrich_wallet and enrich_token.

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

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

The description clearly indicates the use case (batch enrichment of 1-25 addresses) and provides a explicit limit. However, it does not explicitly contrast with single-enrichment tools or mention when not to use this tool, so it stops short of a full alternatives discussion.

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

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

No annotations are provided, so the description carries full burden. It discloses key behavior: statelessness, caller-owned cursor, and the full list of alert types. However, it doesn't mention whether the watchlist is optional or describe the return format, which leaves some gaps.

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

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

The description is four dense sentences, front-loaded with the core purpose. Every sentence contributes: what it does, how to call it, what alerts to expect, and the stateless behavior. 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 tool with 3 parameters and no output schema, the description is fairly complete: it explains the event types, severity grading, and cursor ownership. It lacks explicit return-format details and the optionality of the watchlist, but those are minor given the moderate complexity.

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 the baseline is 3. The description adds helpful context about tokens/wallets as a watchlist and the 'since' as a cursor, but the schema already documents these parameters well. The added alert-type list enriches understanding but doesn't deeply change parameter semantics.

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 'Poll-based event detection covering spot + Jupiter Perps', which states a specific verb (detect/check) and resource (events on spot and Jupiter Perps). It lists exact alert types and is clearly distinct from sibling tools, none of which mention alerts or polling.

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

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

The description clearly implies a polling pattern: pass a since timestamp, get alerts since then, and update the timestamp as a cursor. It doesn't explicitly exclude alternatives or mention when-not to use, but the tool is unique among siblings so the guidance is sufficient.

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

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

There are no annotations, so the description carries the transparency burden. It adds useful context about the analysis dimensions and output format, but it does not disclose methodology, data sources, edge cases, or any side effects (e.g., whether it makes external calls or requires specific token standards). This is a read-only analysis tool, but the description is thin on behavioral details.

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

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

A single, focused sentence that front-loads the verb and resource, lists specific metrics, and states expected outputs. Every word contributes to understanding the tool's function.

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

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

For a simple tool with one parameter and no output schema, the description adequately explains what it does, the inputs it expects, and what it returns. It could benefit from clarifying the exact output structure (e.g., ranking order, risk scale) but is otherwise complete for its complexity.

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 description for 'mints' already clearly states '2-3 token mint addresses to compare' (100% coverage). The textual description reinforces the count and purpose but adds no new semantic information beyond what the schema provides. 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?

The description clearly states the tool performs a side-by-side comparison of 2-3 tokens, enumerates specific dimensions (price, liquidity, volatility, holder concentration, risk), and mentions outputs (rankings, summary picks). This distinguishes it from single-token tools like enrich_token or token_trend.

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

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

The description implies the tool is for comparing multiple tokens but does not explicitly state when to use it over alternatives or any exclusions. It lacks guidance such as 'use this when you need to directly compare token fundamentals' or any mention of alternatives.

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

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only lists outputs (portfolio, activity, risk, labels, rankings, summary picks) but does not disclose side effects, permission requirements, rate limits, or whether it is a read-only operation. For a tool that likely performs enrichment, this is a significant gap.

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

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

The description is two concise sentences with no filler. It front-loads the core function ('Side-by-side comparison') and efficiently lists the compared aspects and outputs. Every word earns its place.

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

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

With no output schema, the description should explain the return values more fully. It mentions 'rankings and summary picks' but does not detail how the comparison is presented or what 'depth' affects. Given the moderate complexity and missing output schema, the description is adequate but leaves gaps.

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

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

Schema description coverage is 100%, so the schema already documents both parameters. The description adds context about the comparison scope but does not clarify the meaning of the 'depth' parameter (light vs full), leaving ambiguity that the schema does not resolve. Baseline 3 is appropriate given the high schema coverage.

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

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

The description clearly states a specific verb ('comparison') and resource ('wallets'), with explicit scope ('2-3 wallets') and content areas (portfolio, activity, risk, labels). It distinguishes itself from sibling tools like enrich_wallet (single wallet) and compare_tokens (tokens).

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

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

The description implies use when comparing multiple wallets, but does not explicitly state when to use this over alternatives or exclude cases. There is no mention of alternatives or prerequisites, so it relies on the agent inferring the 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?

With no annotations, the description carries full responsibility for behavioral disclosure. It reveals the proprietary SolEnrich query stream, real-time nature, and the two distinct output modes, which is useful context. It lacks details on rate limits, data freshness guarantees, or how 'trend' is computed, but overall it is fairly transparent.

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

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

Three sentences with no redundancy: the first states the core function, the second adds provenance, and the third gives usage modes and windows. Every sentence earns its place, making it highly concise and well-structured.

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

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

Without an output schema, the description reasonably covers return expectations by mentioning top-N, rank/percentile/trend, and windows. It could provide an example or specify the response format, but it is sufficient for the tool's moderate complexity.

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 provides 100% parameter coverage with descriptions, so the baseline is 3. The description adds value by clarifying that passing `address` yields rank/percentile/trend and that omitting it gives top-N, which goes beyond the schema's 'single-entity report' 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 clearly identifies the tool as surfacing current query activity from other agents, which distinguishes it from price or money-flow tools. It also specifies two modes (address vs. top-N) and names the proprietary data source, making its role unambiguous among the sibling tools.

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

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

The description explains how to use the tool (omit address for top-N, pass address for a single-entity report) and the available time windows, but it does not explicitly contrast it with sibling tools or state when not to use it. While the context is clear, there are no named alternatives or exclusions.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It lists analysis dimensions but fails to mention read-only nature, data sources, or whether the tool produces a signal or recommendation. It does not describe any side effects or limitations.

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

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

The description is a single, well-structured sentence that front-loads the primary purpose ('Analyze a wallet's trading performance') and then lists specific metrics. It is concise 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?

The tool has no output schema and no annotations, so the description needs to explain what to expect. It lists analysis areas but omits the output format (e.g., does it return a signal, a score, or raw metrics?) and how it differs from related wallet tools. This leaves significant gaps for an agent to select and invoke 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 description coverage is 100% for both parameters (address and lookback_days). The description does not add much beyond the schema, but it does mention the trading metrics, which are more about outputs than parameter semantics. Since schema already documents parameters well, a 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 analyzes a wallet's trading performance with specific metrics (win rate, PnL, consistency, hold time, smart_money classification). It uses a specific verb ('Analyze') and resource ('wallet's trading performance'), but does not explicitly differentiate from sibling tools like wallet_history or compare_wallets.

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

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

The description implies usage for evaluating a wallet's trading performance, which fits the tool name 'copy_trade_signals', but it does not explicitly state when to use this tool over alternatives or provide exclusions. No sibling tool comparisons or context are given.

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

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

With no annotations provided, the description relies on the term 'research' to imply read-only behavior. It lists the analytical outputs but does not disclose operational details such as data sources, latency, or side effects, which are part of the full burden without annotations.

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

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

The description is a single, well-structured sentence that front-loads the purpose ('Comprehensive token research') and then lists specific deliverables. Every word adds value with no redundancy.

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

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

The description adequately conveys what the tool returns by naming the key components (security audit, holder concentration, whale activity, risk score, verdict). Although no output schema exists, it does not specify the exact format or structure of the response, which would be beneficial for a comprehensive tool.

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

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

Schema coverage is 100% and the only parameter 'mint' is fully described in the schema as 'Token mint address (base58)'. The description adds no additional meaning or usage context for the parameter.

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 performs comprehensive token research and enumerates specific outputs (security audit, holder concentration, whale activity, risk score, verdict). This distinguishes it from sibling tools like enrich_token or whale_watch by emphasizing a holistic due diligence report.

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

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

The description implies use for full token due diligence but does not explicitly state when to use it over alternatives or provide exclusions. No sibling tools are mentioned as alternatives.

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

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

With no annotations, the description carries the full burden. It is transparent about the data analyzed and returned, and the verb 'Analyze' strongly implies a read-only operation. However, it does not explicitly state that the tool is non-destructive, nor does it mention any potential costs, rate limits, or data source dependencies, which would make it fully transparent.

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

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

The description is a single, dense sentence that front-loads the core purpose and then lists all key analyses. Every element is informative, with no filler or redundancy. It is concise while conveying substantial detail.

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

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

Given the tool has no output schema, the description appropriately enumerates the expected return values and even specifies position sizes for slippage estimates. This provides enough context for an agent to invoke the tool and interpret results. It lacks some details about error cases or data sources, but overall it is fairly complete for its complexity.

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 provides 100% documentation for both parameters (mint and include_holders), so the baseline is 3. The description adds no extra meaning to the parameters; it only highlights the holder concentration metric, which is an output, not a parameter insight. Thus, no value beyond what the schema gives.

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

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

The description uses a specific verb ('Analyze') with a clear resource ('Solana SPL token') and enumerates the exact metrics returned (price, market cap, liquidity, holder concentration, slippage, risk flags, Jupiter verification). This distinguishes it clearly from sibling tools like enrich_wallet or token_trend.

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

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

The description clearly implies when to use the tool: for deep token analysis, given the extensive list of metrics. However, it does not explicitly state when not to use it or mention alternatives like token_trend or compare_tokens, so it stops short of full usage differentiation.

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

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

With no annotations, the description carries the full burden of safety disclosure. It clearly signals a read-only 'Get' operation and lists included data, but does not mention limitations, rate limits, or caveats about risk score computation. It is adequate but not rich in behavioral detail.

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

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

The description is a single, front-loaded sentence that immediately states the action and then enumerates the profile contents. Every element earns its place with no redundancy.

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

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

For a read-only tool with two well-documented parameters, the description provides a reasonable list of output categories, effectively communicating the return value. It falls short of a 5 only because it lacks any usage context or differentiation from similar wallet tools.

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

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

Schema description coverage is 100%, so the schema documents both the address and depth parameters fully. The description adds no additional parameter-specific meaning beyond the schema, so the baseline of 3 applies.

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

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

The description uses a clear verb 'Get' and specifies the resource (Solana wallet profile) with a list of concrete data points (SOL balance, token holdings, DeFi positions, labels, risk). This distinguishes it from sibling tools like enrich_token (token-focused) and wallet_history (transactions).

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

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

No guidance is provided on when to use this tool versus alternatives like wallet_graph, wallet_history, or compare_wallets. The description lacks any 'use this when' or 'instead of' context, leaving the agent to infer the appropriate use case.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It details the factors considered (sell pressure, buy-rate deceleration, volume fade, etc.), states that rug triggers override all else, and includes a disclaimer (NFA). It does not mention rate limits or authorization requirements, but the tool is clearly read-only and the inputs/outputs are described. This is good transparency for a tool without 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 well-structured and concise, opening with the core purpose and then listing the factors considered and the override conditions. Every sentence contributes value, with no redundancy or filler. The disclaimer 'NFA' is a meaningful qualifier. It is appropriately sized for the complexity of 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?

The description covers the tool's purpose, inputs, outputs (EXIT/DERISK/HOLD, score, reasoning), key factors, and overrides. It does not detail the exact scale of the 0-1 score or provide interpretation of the labels, but given the absence of an output schema, this is acceptable. The description is sufficient for an agent to know when and how to call the tool, though a bit more on output interpretation could push it to a 5.

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 clear descriptions for both parameters (mint and entry_price_usd), and the schema coverage is 100%. The description does not add additional semantic information beyond what the schema offers. For example, it mentions 'pass a mint' but doesn't clarify formats or constraints beyond the schema. Since the schema is complete, a score of 3 is appropriate per the rubric.

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

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

The description clearly states the tool's function: it provides a sell-side verdict for a token, returning EXIT/DERISK/HOLD with a 0-1 score and reasoning. It specifies the input (mint) and distinguishes itself from potential siblings like consensus_signal by focusing on exit decisions. The verb 'get' and the resource 'verdict for a token you hold' are specific and unambiguous.

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

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

The description implies when to use it: when you hold a token and need a sell-side verdict. It mentions it works on any token age, but does not explicitly state when not to use it or suggest alternatives. There is no direct comparison to sibling tools, but the context is clear enough to infer appropriate usage.

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

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

With no annotations provided, the description carries the transparency burden. It discloses caching (24h), lazy population on cache miss, and the short-circuit behavior for unchanged polls. This adds meaningful context beyond what the schema provides, though it omits details like rate limits or return format 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?

The description is two sentences, front-loaded with the core purpose, and contains zero waste. Every clause adds value, from 'daily intelligence brief' to the caching and parameter usage notes.

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

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

For a simple tool with one optional parameter and no output schema, the description adequately explains the product type, data source, and polling behavior. It could be more explicit about the exact content of the brief (e.g., token list, scores), but it is sufficient for an agent to understand the core use case.

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 `since` fully, including the unchanged=true response behavior. The description's 'short-circuit on no-change polls' is semantically equivalent and adds no new information. Since schema coverage is 100%, a 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 delivers a 'daily intelligence brief' consisting of a 'pre-computed ranking of trending Solana tokens with composite-signal scoring.' This specific verb+resource distinguishes it from sibling tools like new_tokens or trending_signals, which focus on different aspects.

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

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

The description implies use for periodic polling of daily trending tokens and instructs to pass `since` to short-circuit on no-change polls. It gives clear context but does not explicitly name alternatives or when not to use this tool, earning a 4 rather than 5.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It explains that the tool computes net EV after exit costs, presents a verdict, and includes a disclaimer ('NFA'). It does not detail data freshness or rate limits, but the core analytical behavior is transparent and safe.

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

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

The description is two sentences long and front-loads the primary purpose, then follows with methodology and return-value information. Every clause adds value, and there is no filler or redundancy.

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

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

Given the lack of an output schema, the description adequately explains the return verdict ('POSITIVE_EV / HOUSE_EDGE / NEGATIVE_EV') and the main evaluation dimensions. It leaves machine-code specifics to the schema, but the overall concept is sufficiently clear for an agent to select and invoke 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?

The schema covers all four parameters (100% coverage), but the description adds meaningful semantics by explaining the buyback floor (85-93% of insured value, ≤72h) and marketplace fee (2% + fill-risk). This enriches the meaning of the exit_strategy parameter and clarifies the 'net edge' concept, going beyond the schema definitions.

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 ('Scan') and resource ('Jupiter Gacha (Collector Crypt) tokenized-card packs'), clearly stating the tool's purpose. It explicitly defines the computation (net-of-exit expected value) and the verdict types, making it easy to distinguish from sibling tools that focus on generic tokens or wallets.

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

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

The description provides clear context for when to use this tool: to evaluate the realizable EV of Gacha packs, with a comparison of exit strategies. It does not explicitly name alternative tools or exclusion criteria, but the sibling list contains no overlapping Gacha/EV scanner, so the context is sufficient.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It transparently explains the filtering process (excludes market-makers + dust), the aggregation into per-coin consensus metrics, and explicitly labels the output as a positioning signal rather than a trade. This provides a clear and honest account of the tool's behavior.

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

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

The description is compact and information-dense, with every sentence contributing to understanding. It front-loads the core purpose, then details methodology, parameters, and usage guidance without any 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?

As there is no output schema, the description compensates by describing the output components (long/short counts, net notional, bias, conviction, top-trader drill-down). It also covers the parameter and the tool's strategic context, making it complete for a read-only analysis tool.

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

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

Schema coverage is 100% for both parameters, so the schema already explains `market` and `top_traders`. The description adds minor context for `market` by stating 'Optionally focus one coin via `market`', but does not significantly enrich parameter understanding beyond the schema.

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

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

The description clearly states the tool's purpose: showing where Hyperliquid smart money is positioned. It specifies the methodology (filtering leaderboard to consistent directional traders, excluding market-makers and dust) and the output (per-coin consensus and top-trader drill-down), which distinguishes it from sibling tools like consensus_signal or smart_money_flow.

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

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

The description gives explicit guidance on when to use the tool: as confluence/risk context, not as a standalone entry. It also explains the optional `market` parameter usage. However, it does not explicitly name alternative tools for when not to use it, just states what it's not for.

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

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

With no annotations, the description carries the full burden. It discloses that data is live, read from public on-chain state, and provides a comprehensive list of output fields including account-level metrics and historical PnL. It does not mention rate limits or edge cases, but for a read-only public data tool, the behavioral traits are sufficiently conveyed.

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

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

The description is three sentences with no wasted words. It front-loads the core purpose, then lists specific output fields, and ends with the strategic role. Each sentence earns its place, making it highly concise and well-structured.

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

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

Despite having no output schema, the description thoroughly enumerates what the tool returns (per-position fields, account value, bias, profile, PnL timeframes), which is sufficient for an agent to understand the data. The single-parameter input is simple, and the description gives enough context for usage. It is complete for the tool's complexity.

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 provides 100% coverage of the single parameter, with the description 'Hyperliquid EVM (0x) address' being clear. The tool-level description adds context about the address being for perp positions, but does not add parameter-specific details beyond the schema. 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 retrieves live Hyperliquid perp positions for an EVM address, and enumerates the specific data points (side, leverage, notional, entry, PnL, etc.). It distinguishes itself from siblings by explicitly mentioning Hyperliquid, EVM (0x) addresses, and positioning as the building block for smart-money tracking, which separates it from tools like hyperliquid_smart_money or perps_trader_profile.

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

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

The description provides clear context that this is a lower-level, per-address data tool ('building block for HL smart-money tracking'), implying it should be used when granular per-position data is needed. However, it does not explicitly name alternative tools for when to use them instead, so it lacks explicit exclusions or direct comparisons.

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

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

No annotations are provided, so the description carries the full burden. It discloses key behaviors: filtering by liquidity and risk score, and ranking safest first. However, it does not describe return format, pagination, data freshness, or any limitations (e.g., source of tokens, time window for 'recently launched'). This is adequate for a simple read-only list tool but leaves some gaps.

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

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

The description is a single, concise sentence that front-loads the primary purpose ('Discover recently launched Solana tokens') and includes key details without fluff. Every word earns its place, making it highly scannable for an AI agent.

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

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

Given the tool's simplicity (3 optional parameters, no output schema), the description covers the essential context: what the tool does, how results are filtered and ordered. It lacks mention of output shape or additional constraints, but for a straightforward listing tool, this is sufficiently complete. A more detailed description would be beneficial but is not necessary.

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 fully documents all three parameters with descriptions (100% coverage). The description adds a link between the filters (liquidity and risk) and the parameters, and mentions the safety ranking, but does not provide additional parameter-level meaning beyond the schema. The baseline of 3 applies due to high schema coverage.

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

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

The description clearly states the tool's function: 'Discover recently launched Solana tokens.' It specifies the resource (Solana tokens) and the action (discover), and adds distinguishing details (recently launched, filters, ranking). While it doesn't explicitly name sibling tools, the unique scope and sorting criteria set it apart from generic feed tools like 'feed_latest'.

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

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

The description implies when to use the tool: when you want recently launched tokens filtered by liquidity and risk, ranked safely. However, it provides no explicit guidance on when not to use it or which sibling tools to prefer (e.g., 'feed_latest' for general feeds, 'trending_signals' for trends). The usage context is inferred 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?

With no annotations, the description carries the full burden. It discloses the data categories returned (type, transfers, accounts, fees) but does not mention side effects, error behavior, or dependencies such as network access. Since 'parse' implies a read-only operation and no mutations are described, this is acceptable but not thorough.

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

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

The description is a single, front-loaded sentence that states the action and resource immediately, followed by a compact, comma-separated list of the parsed components. Every word earns its place with zero 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 one-parameter tool with high schema coverage and no output schema, the description adequately sets expectations by listing the categories of data returned. It does not cover edge cases like invalid signatures or error responses, but these are not critical for a basic parse operation.

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 fully describes the sole parameter 'signature' including format and length, achieving 100% schema description coverage. The tool description adds no additional parameter-specific context, so the baseline score 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 uses a specific verb ('Parse') with a clear resource ('a Solana transaction') and enumerates the extraction scope ('type, protocol, SOL/token transfers, accounts involved, and fee details'). This clearly differentiates it from the sibling tools, which are focused on analytics, signals, or wallet/token enrichment.

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

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

The description implies usage when a detailed breakdown of a specific transaction is required, but it does not provide explicit guidance on when to use this tool versus alternatives like 'query' or 'batch_enrich'. No exclusions or alternative recommendations are mentioned.

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?

Given no annotations, the description carries the full burden. It discloses that pool perps are flagged as not viable due to borrow on both sides, and that returns include per-venue trade, filtered opportunities, and best trade. This adds behavioral context beyond a simple computation description, though it doesn't cover edge cases like no opportunities.

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

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

The description is three sentences, front-loaded with the core function, followed by methodology detail and output structure. Every sentence contributes value, with no redundancy or fluff.

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

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

With no output schema, the description summarizes the return structure (per-venue trade, filtered opportunities, best trade) and explains the filtering logic for venue viability. It lacks details on edge cases like no opportunities, but is adequate for a tool with only two parameters and a straightforward scope.

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

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

Schema coverage is 100% with clear parameter descriptions (asset, min_yield_apr_pct). The description adds context about filtering by yield and viability but does not provide additional syntactic detail beyond the schema. Baseline 3 is appropriate as the schema handles parameter semantics.

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 computes perp mark vs spot price across venues and surfaces actually-earnable yield, with a specific output structure (per-venue trade, filtered opportunities, best trade). This distinguishes it from sibling tools like perps_cross_venue_funding by focusing on net yield after borrow and viability filtering.

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

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

The description provides context on venue types (funding-rate vs pool perps) which implies when this tool is relevant, but it does not explicitly state when to use it over alternatives or mention sibling tools. It gives clear context but no exclusions, so a score of 4 is appropriate.

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

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

With no annotations provided, the description carries the full burden. It discloses what the tool returns (best entry, basis, arbitrage) and notes venue-specific availability for assets. However, it doesn't mention whether it's read-only, potential latency, or error conditions, though the verb 'compare' implies a safe read. It adds useful context beyond just the schema.

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

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

Three concise sentences, front-loaded with the primary function, followed by return values and supported assets. No unnecessary words; every sentence adds 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 2-parameter tool with no output schema and no annotations, the description covers the main functionality, returns, and supported assets. It lacks explicit details on output formatting or edge cases, but the information given is sufficient for basic use. The venue-specific availability caveat is a nice addition.

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 parameter descriptions already explain 'market' and 'include_reference'. The description adds only a marginal note about venue-specific availability, which relates to the market enum. No additional syntax or format details are provided, so the 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?

The description clearly states a specific verb ('Compare') with a clear resource ('borrow/funding APR + OI across venues'), and lists supported assets. It also distinguishes from siblings by specifying cross-chain reference venues (Hyperliquid, dYdX v4), which differentiates it from the broader perps_venue_comparison tool.

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

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

The description implies usage for cross-venue funding comparison but does not explicitly state when to use it over sibling tools like perps_venue_comparison, nor does it mention any exclusions or alternatives. Only context is the functionality itself.

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

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

With no annotations, the description carries the behavioral disclosure burden. It states it reads on-chain Anchor accounts directly, revealing a read-only nature and data source, which is useful context. It stops short of explaining health flag semantics or data freshness, but the core behavior is transparent.

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

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

The description is a single sentence packed with precise details—metrics, venue, assets, and data source—without any waste. It is well-structured and immediately informative.

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

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

For a zero-parameter tool, the description fully enumerates the output fields and scope, making it self-contained even without an output schema. It tells the agent exactly what data to expect.

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

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

The tool has zero parameters, so the input schema already covers everything. The description adds no parameter-specific details, but none are needed; a baseline of 4 is appropriate for a parameter-less tool.

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

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

The description names specific metrics (OI, utilization, borrow APR, skew, OI caps, health flags) and explicitly scopes them to Jupiter Perps SOL/BTC/ETH, making the tool's purpose clear and distinct from siblings like perps_market_trend or perps_venue_comparison.

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

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

It provides clear context for when to use the tool—when a snapshot of Jupiter Perps market structure metrics is needed—but does not explicitly contrast it with alternative perps tools or state when not to use it.

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

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

With no annotations, the description carries the full burden. It discloses the computation (deltas, direction indicators), the exclusion of mark price from overall direction, and the available lookback periods. It does not explicitly state it is read-only or mention data availability limitations, but the context is sufficient for a data analysis tool.

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

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

The description is two sentences long and front-loaded with the key output metrics and lookbacks. The second sentence adds direction indicators and the intended use case. No filler or repetition.

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

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

For a tool with one parameter and no output schema, the description explains what metrics are returned, how direction is interpreted, and the intended use case. It lacks an explicit statement about the output structure or how to distinguish from perps_market_structure, but it is complete enough for an agent to select and invoke correctly.

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

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

The only parameter (lookback) has 100% schema coverage with a clear description ('History window') and enum values. The tool description mentions 'over 7/14/30 days' which aligns with the schema but adds little beyond it. Baseline 3 is appropriate since the schema already provides full semantics.

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 specifies the resource (Perps market trend for SOL/BTC/ETH), the metric deltas (mark price, OI, skew, utilization, borrow APR), and the lookbacks (7/14/30 days). It also states the output includes direction indicators and overall direction, making it distinct from sibling perps tools like perps_market_structure or perps_basis_signal.

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

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

The description gives an explicit use case: 'Use for regime detection — bots that adjust behavior based on whether markets are growing, stressed, or rebalancing.' This clearly tells an agent when to invoke the tool, though it does not explicitly exclude alternatives or compare with siblings.

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

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

With no annotations, the description carries the burden of disclosing behavioral traits. It does disclose a meaningful limitation (Adrena PnL is null when mark prices are unavailable) and lists classification and risk flags. However, it never explicitly confirms this is a read-only operation, and the 'Open positions' phrasing leaves ambiguity about whether it executes trades.

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

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

The description is four dense sentences, each adding distinct information: purpose, venue breakdown, classification/risk flags, and the Adrena PnL caveat. There is no filler, and the most important purpose appears first.

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

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

For a tool with no output schema and no annotations, the description covers the main return elements well: per-venue positions, combined totals, tags, classification, directional bias, exposure flag, risk flags, and a specific edge case. It could mention empty-wallet behavior or the top-level return shape, but the coverage is strong.

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 fully describes the single 'address' parameter as a Solana wallet address, and the description adds minimal semantic value beyond restating 'wallet'. No format, validity, or network details are added.

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

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

The description clearly states the tool provides open positions across Jupiter Perps and Adrena for a wallet, and it distinguishes itself from siblings by naming both venues and enumerating rich output fields. However, it lacks an explicit retrieval verb like 'Gets' or 'Lists', and 'Open positions' could be misread as an action rather than a noun phrase.

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

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

The description implies it should be used for wallet-level perps positions across Jupiter and Adrena, but it never explicitly states when to use it over sibling tools such as hyperliquid_trader_profile or perps_venue_comparison. There are no usage exclusions or alternative recommendations.

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

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

With no annotations provided, the description carries the full burden of disclosing behavior. It explains the analysis inputs and output (rankings + recommendation + warnings), which is useful, but it does not state whether the tool is read-only, how warnings are determined, or any limitations (e.g., venue coverage, data freshness). This is adequate but not thorough.

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

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

The description is concise and well-structured: a one-sentence value proposition, a sentence listing the key factors used, and a sentence stating the output format. Every sentence earns its place with no fluff or repetition.

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

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

For a tool with moderate complexity and no output schema, the description covers the main aspects: inputs, decision factors, and output structure (rankings + recommendation + warnings). However, it lacks details about which venues are compared, what the warnings mean, or how rankings are derived, leaving some gaps for the agent.

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

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

The input schema already provides full descriptions for all three parameters (100% coverage), so the baseline is 3. The description adds meaning by connecting size_usd to 'spot slippage' and 'OI cap headroom', clarifying why size matters beyond the schema's generic 'Position size in USD'. This extra context justifies a 4.

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 clear value proposition ('Where to trade this market at this size') and specifies the tool's function: compare perps venues using funding, slippage, fees, OI headroom, and entry cost, then return rankings and a recommendation. This distinguishes it from siblings like perps_cross_venue_funding by explicitly extending beyond funding with additional factors.

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

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

The description implies the usage scenario: deciding where to execute a trade of a given market and size. It also hints at being a more comprehensive alternative to perps_cross_venue_funding ('Builds on cross-venue funding...'), but it does not explicitly state when not to use it or name alternative tools for simpler funding-only comparisons.

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

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

No annotations are present, so the description must carry the full burden. It details the output contents (daily snapshots of value, balance, holdings, risk score, and summary stats) but does not explicitly state that this is a read-only, non-mutating operation or mention any permissions or rate limits. The output detail helps, but the lack of explicit behavioral disclosure leaves some ambiguity.

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

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

The description is two sentences with no filler; the first sentence packs in the core scope and output details, and the second gives a clear use case. It is slightly dense but well-organized and appropriately concise.

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

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

For a simple 2-parameter tool with no output schema, the description is fairly complete: it covers purpose, key inputs, output fields, and supported periods. It does not mention pagination, units, or timezone behavior, but these are minor for this tool type.

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 provides 100% coverage for both parameters (address and period), including enum values for period. The description reinforces these fields ('over 7/14/30 days' and 'wallet') but adds little beyond what the schema already states, so 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 identifies the tool as providing a full portfolio time-series for a wallet, enumerating data points and supported periods. However, it lacks a strong verb like 'returns' or 'fetches' and does not explicitly differentiate from sibling tool wallet_history.

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 states an explicit use case: 'For charting and PnL tracking,' which gives clear context for when to use it. It does not mention when not to use it or alternative tools, but the use-case guidance is valuable.

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

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

No annotations are provided, so the description must fully disclose behavioral traits. It enumerates data categories but does not state whether the operation is read-only, describe return format, pagination, rate limits, or handling of unsupported protocols. This leaves significant behavioral ambiguity for an analytics tool.

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 exceptionally concise: two sentences that front-load the core purpose and data categories, followed by supported protocols. Every word contributes value, with no repetition or filler.

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

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

For a two-parameter tool without an output schema, the description provides a reasonable overview of the data scope. However, it lacks details on return shape, error cases, or any additional behavior, and with no annotations, the agent has limited context for invoking the tool in complex workflows.

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 documentation already covers both parameters thoroughly (protocol slug or Solana program ID, include_yields boolean with default). The description adds a broader list of supported protocol examples ('Raydium, Orca, marginfi...'), which is helpful but does not alter the baseline established by 100% schema description coverage.

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

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

The description clearly identifies the tool as providing DeFi protocol analytics with specific data types (TVL, yield pools, on-chain activity, health signals) and a list of supported protocols. This makes the purpose clear and distinguishes it from sibling tools focused on tokens or wallets, though it lacks a direct action verb.

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

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

The description does not provide explicit guidance on when to use this tool versus alternatives. It lists supported protocols, which implies a target use case, but there is no mention of when not to use it or how it compares to sibling analytics tools like compare_tokens or token_trend.

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

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

With no annotations provided, the description carries the full burden. It discloses the orchestration behavior (routing to enrichers, chaining parallel intents, returning a unified briefing), which is valuable. However, it does not mention error handling, ambiguity resolution, or limitations (e.g., unsupported question types). This is acceptable 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?

The description is a single, tightly packed paragraph that front-loads the core purpose and follows with concrete examples. Every sentence earns its place—no fluff, no restating of the tool name, and the examples are illustrative rather than redundant.

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

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

Given the tool's orchestrator role and the absence of an output schema, the description provides a clear mental model of how input maps to behavior (routing and chaining) and indicates the output type ('unified briefing'). It could add a bit more about the content or structure of the briefing, but overall it's sufficiently complete for a query tool.

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

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

The schema already defines the 'question' parameter at 100% coverage. The description adds significant semantic value by enumerating example intents ('should I buy <mint>?', 'wallet deep dive', 'SOL-PERP funding rate') that clarify what constitutes a good question, which goes beyond the schema's minimal 'natural language question' description.

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

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

The description clearly states the tool's purpose: to ask plain English questions about Solana wallets, tokens, or markets. It goes beyond a simple definition by explaining the routing behavior (single-intent to one enricher, compound to chained enrichers) and provides concrete examples, making it highly distinguishable from the 30+ sibling tools.

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

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

The description clearly implies when to use this tool: for natural language questions that may require one or multiple data points, with examples showing how to phrase intents. It lacks explicit 'when not to use' or direct mentions of alternative tools, but the routing explanation and examples effectively convey its role as a general-purpose entry point.

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

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

With no annotations, the description carries the full burden and does so admirably. It discloses the specific metrics measured (buy-rate acceleration, buy pressure, volume/price velocity, holder growth, liquidity trend), the classification categories, and the additional risk flags (already-ran tokens and liquidity pulls). This goes far beyond a generic 'scan' and gives agents a clear model of behavior.

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

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

The description is about 50 words across two sentences. It front-loads the core purpose as a question, then efficiently lists the measured factors and classification output. Every sentence earns its place with no redundancy or fluff.

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

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

For a complex analytical tool with four parameters and no output schema, the description provides a solid understanding of what it does and what it returns (score and reasoning, classification). It could slightly improve by explicitly stating return structure (e.g., list of tokens), but the classification and score mention covers the essential output. Given the complexity, this is quite complete.

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

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

Schema description coverage is 100% with clear parameter descriptions. The description adds some context by relating 'fresh' to token age and mentioning liquidity trend, but it doesn't provide additional syntax or format details beyond the schema. Baseline 3 is appropriate since the schema already handles parameter semantics effectively.

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 what the tool does: identifies fresh Solana memecoins that are accelerating. It specifies the resource (fresh Solana memecoins), the action (measuring acceleration and classifying), and provides a specific classification scheme (RUNNING/IGNITING/PARABOLIC_LATE/FADING). This distinguishes it well from siblings like new_tokens or token_trend, which focus on other aspects.

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

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

The description implies a clear use case: finding memecoins with accelerating momentum. It does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions. However, the specific metrics and classification make it evident that it's for momentum scanning, which provides clear context. Missing explicit alternatives keeps it from a 5.

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

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

With no annotations, the description must reveal behavior, but it only lists three high-level actions (score, surface, map) without detailing output format, data sources, limitations, or unexpected behaviors. The schema parameters already imply most of the behavior, so the description adds little transparency.

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

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

The description is two sentences with no fluff. The first sentence grabs attention, and the second succinctly lists the core capabilities. Every word earns its place.

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

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

The tool has five parameters and no output schema, yet the description does not explain what the tool returns or how to interpret the results (e.g., a ranked list, a graph structure, etc.). This is a significant gap for an agent deciding how to use the 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?

The schema covers 100% of parameters, but the description adds conceptual context: 'copy-trade metrics' ties to min_win_rate and lookback_days, 'tokens accumulating' maps to top_n_tokens, and 'wallet clusters' relates to include_graph. This enriches understanding beyond the schema.

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

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

The description clearly states it scores Solana wallets by copy-trade metrics, surfaces accumulated tokens, and maps wallet clusters, using specific verbs and resources. It distinguishes itself from similar siblings like copy_trade_signals by focusing on high-performing wallets and cluster analysis.

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 phrase 'Where high-performing Solana wallets are moving' implies a use case for tracking smart money flow, but it does not explicitly state when to use this tool over alternatives like smart_money_trenches or copy_trade_signals. No exclusions or alternative guidance is provided.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does disclose key methodology (vetted realized-PnL winner seed set, bot-filtered, ranking by distinct smart buyers + recency), which adds value. However, it lacks details on data freshness, update frequency, or limitations (e.g., how 'proven-winner' is defined, potential biases), leaving room for ambiguity.

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

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

The description is concise (two sentences) and front-loaded with the core question. It packs significant information without wasted words. However, the use of jargon ('aping', 'trenches', 'pre-ape') might reduce clarity for some users, though it remains efficient. No unnecessary fluff.

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

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

The tool has 4 fully described parameters, no annotations, and no output schema. The description covers the purpose, methodology, and ranking order, which is fairly complete for a screening tool. However, it does not specify the output format (e.g., what fields are returned for each token), which the description would need to compensate for the missing output schema. This gap prevents a higher score.

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 the baseline is 3. The description adds minimal parameter-specific semantics beyond what's in the schema; it mentions 'fresh (<6h)' corresponding to max_token_age_hours and 'recent buys' aligning with hours_back, but these are already clearly documented in the schema. No additional meaning is needed.

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

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

The description clearly states what the tool does: identifies proven-winner wallets aping fresh (<6h) memecoin launches and what they are buying. It distinguishes itself from siblings by emphasizing 'vetted realized-PnL winner seed set (bot-filtered)' and 'Pre-ape attention signal', making it unique among similar tools like smart_money_flow or copy_trade_signals.

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

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

The description provides clear context for when to use this tool—when looking for early signals of fresh memecoin launches being bought by proven smart wallets. It implies a niche use case (pre-ape attention) and differentiates from broader alternatives through terms like 'proven-winner wallets' and 'bot-filtered', but it does not explicitly state when not to use it or name alternatives.

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

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

With no annotations provided, the description carries the full burden. It discloses the tool's read-only nature by describing it as a metrics provider and adds context about daily snapshots and direction indicators. However, it does not specify the exact metrics included, the output format, or any access requirements, leaving some gaps.

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

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

The description is a single concise sentence that front-loads the core purpose ('Token metrics over time') and includes relevant detail about snapshots and direction indicators. Every word earns its place, with no unnecessary fluff.

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

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

The description provides a sufficient high-level understanding of the tool's function and return type (daily snapshots) given the simple two-parameter schema. It lacks specifics on which metrics are tracked and the exact output structure, but the absence of an output schema makes this a minor gap rather than a critical omission.

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 covers both parameters with descriptions (mint and lookback). The description adds no additional semantic detail beyond implying that lookback is used for time periods. Since schema coverage is 100%, the baseline score 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 that the tool provides token metrics over time with daily snapshots and direction indicators per metric. It distinguishes itself from sibling tools like compare_tokens (which compares tokens) and enrich_token (which likely gives a single snapshot) by emphasizing the temporal dimension.

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

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

The description implies usage for trend analysis ('over time', 'direction indicators') but does not explicitly state when to use it over alternatives or provide exclusions. There is no mention of when not to use it or which sibling tool to prefer in other contexts.

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

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

With no annotations provided, the description carries the full burden. It discloses the internal signals (on-chain velocity, proven-winner wallet buys, agent attention) and the verdict scale. It doesn't explicitly state whether the operation is read-only or mention rate limits/errors, but for a check tool the lack of side-effect disclosure is acceptable. The 'NFA' disclaimer adds context.

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

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

The description is compact and front-loaded: the first sentence sets context and outcome, the second lists the data sources, and the third references a partner tool. Every sentence earns its place, with no filler. 'NFA' is a meaningful caveat in crypto contexts.

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

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

For a tool with one parameter, no output schema, and no annotations, the description covers all essential aspects: input, output (verdict categories), reasoning, and the specific signals examined. It even names a complementary tool for a fuller analysis. Enough to invoke correctly without missing critical info.

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

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

Schema coverage is 100% with a single 'mint' parameter described as 'Token mint address to check'. The description adds no further parameter details beyond restating the mint input, so it meets the baseline of 3 without adding extra semantic value beyond the schema.

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

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

The description clearly identifies the verb ('check'), the resource (a token mint), and the output (a verdict with reasoning). It distinguishes itself from siblings by naming its specific signals (on-chain velocity, proven-winner wallet buys, agent attention) and explicitly says it 'Pairs with due_diligence (structural safety)', which differentiates it from that sibling.

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

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

The description explicitly states when to use it ('Before you ape') and that it targets 'that specific token'. It also names a complementary/alternative tool, due_diligence, for structural safety, giving clear usage guidance and excluding general scans or multi-token contexts.

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

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

With no annotations, the description carries the burden of revealing behavior. It explains the scan produces a ranked list with reasoning and verdicts, but does not explicitly state it is read-only, nor discuss rate limits, data freshness, or potential side effects. The term 'scan' hints at safety, but the lack of explicit disclosure limits transparency.

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

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

The description is highly concise and front-loaded: it opens with the purpose ('full memecoin pre-ape scan in one call'), details the three signals, and explains the output and verdicts in two sentences plus 'NFA'. Every sentence adds value and there is no redundant content.

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

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

Given no output schema and no annotations, the description provides a solid overview of return values: a ranked list with per-token reasoning and HIGH_CONFLUENCE/MODERATE/SINGLE_SIGNAL verdicts. It lacks an explicit struct of each token entry, but covers the core output and differentiates from sibling tools, making it reasonably complete.

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

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

Schema description coverage is 100%, so the schema already documents the three parameters (limit, min_liquidity_usd, max_token_age_hours). The tool description adds no parameter-specific information, but the baseline of 3 applies because the schema fully covers parameter semantics.

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 what the tool does: it performs a 'full memecoin pre-ape scan' combining three specific signals (on-chain velocity, smart-money buys, agent attention) into a ranked list with verdicts. This distinguishes it from sibling tools like runner_scan or smart_money_flow, which focus on individual signals.

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

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

The description implies when to use this tool: for a comprehensive pre-ape scan, emphasizing 'full' and 'one call' as an alternative to running multiple individual scans. However, it does not explicitly name alternative tools or state when not to use it, so it lacks explicit 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?

With no annotations, the description carries the full burden. It discloses the composite methodology (DexScreener trending + risk scoring + whale-flow) and mentions reasoning. However, it doesn't specify return format, real-time vs cached, or any side effects, leaving some ambiguity.

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 core purpose, and every word adds value. It's an appropriately concise description.

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 signal tool with no annotations or output schema, the description explains purpose and methodology but omits details about the output structure (e.g., what 'reasoning' includes) and any limitations. It's adequate but not fully complete.

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

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

Schema description coverage is 100%, so the baseline is 3. The tool description adds no additional meaning to parameters like 'max_risk_score' or 'include_whale_watch' beyond what the schema already explains.

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

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

The description clearly states the tool returns a ranked list of Solana tokens with a composite signal. It uses a specific verb ('Composes') and identifies the resource (Solana tokens), but doesn't explicitly distinguish from siblings like 'consensus_signal' or 'feed_latest'.

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: use this to get a ranked list of currently notable Solana tokens. However, the description does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It fails to mention how the graph is constructed, whether the operation is read-only, limitations such as supported chains or depth semantics, or any details about output format or performance.

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

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

The description is a single sentence that is direct and front-loaded with the action verb. It effectively lists the tool's key capabilities without unnecessary 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?

Without an output schema or annotations, the description must provide more context to be complete. It does not explain what a 'connection' is, how results are returned, or how a user should interpret the clusters/patterns. Given the large number of sibling tools, this leaves the tool's role under-specified.

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

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

The input schema already describes both parameters (address and depth) with 100% coverage, so the description adds no new parameter-level information. The baseline score of 3 applies because the schema does the heavy lifting.

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

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

The description clearly states the tool's function with a specific verb 'Map' and resource 'wallet connections', and enumerates three concrete outputs: finding counterparties, detecting clusters, and identifying suspicious patterns. This distinguishes it from sibling tools like 'enrich_wallet' or 'wallet_history' which serve different purposes.

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

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

The description implies usage for network analysis of wallet relationships, but it does not explicitly state when to use this tool instead of alternatives like 'smart_money_flow' or 'whale_watch' which may overlap. No exclusions or alternative recommendations are provided.

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

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

The description provides useful context about the output content (snapshots, position changes, direction indicators) but discloses no behavioral traits such as read-only nature, rate limits, or data granularity. With no annotations provided, the description carries the full burden and partially meets it by indicating the historical/read-oriented nature, but lacks deeper transparency.

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

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

The description is a single concise sentence that immediately conveys the core functionality and adds relevant detail about snapshots, position changes, and direction indicators. Every word earns its place, and the structure is clean.

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

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

For a simple read tool with a complete parameter schema, the description offers a basic understanding of the output. However, without an output schema or annotations, it lacks details on response format, error scenarios, and how it differs from similar tools like portfolio_history, making it only minimally complete.

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

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

The input schema already has 100% coverage with descriptions for both parameters (address and lookback). The description does not add any parameter-specific meaning beyond what the schema provides, so the baseline of 3 applies.

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 what the tool does: shows wallet portfolio over time with snapshots, position changes, and direction indicators. The verb is implied ('get history'), and the resource is specific. However, it does not distinguish from the sibling tool 'portfolio_history', which likely serves a similar purpose, so it misses the differentiation needed for 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?

No guidance is given on when to use this tool versus alternatives. The description is purely declarative and does not mention exclusions, alternatives, or specific use cases. With many sibling tools like portfolio_history and wallet_graph, the lack of any usage direction leaves the agent to guess.

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

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

No annotations are provided, so the description must disclose behavior. It lists the metrics provided but does not state that this is a read-only operation, what data source is used, or any rate limits. It only mentions what is tracked, not how the tool behaves. Score 2.

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

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

The description is a single, front-loaded sentence with a colon-separated list. Every phrase adds value and there is no redundancy. A perfect score for conciseness.

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 tool has no output schema or annotations, so the description must compensate. It covers the main purpose and the type of output metrics. However, it omits any mention of required parameters, return format, or usage context. It is adequate but not complete, so a 3 is appropriate.

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 descriptions cover all 3 parameters with clear meaning (mint, threshold_usd, lookback_hours), so the baseline is 3. The description adds little specific parameter semantics beyond confirming that thresholds relate to whale activity, which is already in 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 uses the specific verb 'Track' and identifies a concrete resource: 'top token holders,' followed by specifics (balances, % supply, buy/sell volumes, accumulation vs distribution). This clearly states the tool's function. It does not explicitly differentiate from sibling tools like smart_money_flow, but the focus on top holders is distinctive enough for a 4.

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

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

There is no guidance on when to use this tool versus alternatives. The description provides no context about scenarios or exclusions, such as 'for large transfers use smart_money_flow.' This is a gap.

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