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

No annotations are provided, so the description carries the burden. It transparently discloses pagination (25 per page), default sorting by net value, the return of top 3 tokens, and sorting options. It does not mention limitations like time-range clamping (covered in schema), but adequately describes observable behavior.

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

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

The description is well-organized with a core intro, methodology note, sorting options, and examples. It is somewhat lengthy due to the methodology note, but each section serves a purpose and the structure aids comprehension.

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

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

With an output schema present and 100% schema description coverage, the description needs only to convey core behavior and usage context. It covers both address and entity query modes, pagination, sorting, and supplementary token data, making it complete for correct invocation.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value by listing sorting fields, noting ASC/DESC support, and providing two complete JSON examples that demonstrate correct parameter combinations. This goes beyond schema descriptions.

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

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

The description clearly states the tool 'Get 25 (per page) addresses or entities with the most common interactions with input addresses' with specific details like default sort and token info. It is specific and distinguishes itself from sibling tools like address_related_addresses by focusing on counterparties and value interactions.

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 'Note: To get related wallets' section provides clear methodology for when to use this tool, including focusing on direct value transfers, CEX deposit addresses, and going one level deeper. While it does not explicitly name alternative tools, it gives strong contextual guidance for the 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 disclosing behavior. It describes return columns, sorting/filtering options, chain constraints, and example input. While it doesn't mention pagination or rate limits, it gives substantial context about what the tool returns and how it behaves, especially the critical EVM vs non-EVM chain handling.

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 information-dense yet well-organized: a concise purpose sentence, bullet-like chain rules, clear column lists, sort/filter details, and a concrete example. Every section earns its place; no fluff or repetition. It front-loads the primary purpose and appends operational details in a scannable format.

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

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

Given the tool's complexity (single-chain constraint, EVM vs non-EVM, spot vs perp, sorting/filtering) and the presence of an output schema (so return values are separately defined), the description covers the essential usage pitfalls and example inputs. Missing details like pagination behavior and default sort direction are left to schema, but the description is largely complete for an agent to 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 0% for the top-level parameter, so the description must compensate. It explains the `chain` parameter's nuanced behavior (required for EVM, auto-detected for non-EVM, 'hyperliquid' value), and describes `order_by` and `valueUsd` filtering. It does not explicitly cover `page` or `dateRange`, but provides an example demonstrating `dateRange` usage, adding significant meaning beyond bare schema field names.

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 ('Get') and clearly identifies the resource ('a wallet's individual trades on a single chain') and scope (DEX swaps or Hyperliquid perpetuals, newest first). It explicitly distinguishes from sibling tool `token_dex_trades` by being wallet-centric, which prevents tool-selection confusion.

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

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

Provides explicit usage context: 'Call once per chain to span multiple networks', 'all'/'evm' unsupported, EVM wallets MUST pass `chain`, non-EVM auto-detected, and 'hyperliquid' for perp trades. It also names the sibling alternative `token_dex_trades` for token-centric needs, giving clear when-to-use and when-not-to-use guidance.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It implies a read-only operation via 'Get' and specifies the historical scope, but it does not explicitly state that it has no side effects, does not describe any data source limitations, or mention that it can analyze entities in addition to addresses. The lack of explicit safety statements is a gap, but the read-only nature is relatively obvious for a balance 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 a single, front-loaded sentence with no filler. Every word earns its place, and it avoids redundancy with the schema and annotations. It is appropriately concise for a tool of this specificity.

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?

While an output schema exists (so return values are covered), the description is minimal for a tool that accepts a nested request object and supports multiple modes (address vs entity, lookback periods). It does not explain when historical balances are needed or mention that both address and entity_id cannot be used together. The description is adequate for a straightforward read operation but lacks contextual depth.

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%—all nested properties have meaningful descriptions. The tool description adds minimal value beyond the schema, only introducing the concepts 'native coin & token.' Since the schema fully documents parameters, 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 uses the specific verb 'Get' and clearly identifies the resource: historical native coin & token balances of an address. The qualifier 'historical' distinguishes it from current-balance sibling tools like address_portfolio, though it omits the fact that it also supports entity_id as an alternative to address.

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 such as address_portfolio or address_transactions. The description only states what the tool does, with no mention of use cases, prerequisites, or exclusions.

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

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

The description discloses some behavioral traits: it mentions output is 'pre-formatted markdown' and that defi/hyperliquid modes 'return raw JSON'. This is contradictory and confusing, creating a behavioral transparency problem. It also does not disclose authentication requirements, rate limits, or error behavior. With no annotations, the description carries the full burden and fails to provide a consistent or complete behavioral picture.

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 with a clear opening purpose, bullet-point modes, entity behavior, output format note, and example usage. It is somewhat longer than necessary but no excessive filler except the last 'This tool provides flexible portfolio analysis...' sentence. Overall it is efficient and front-loaded with the primary purpose.

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

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

The description fails to explain the required 'request' wrapper in the schema, ignores the 'chain' parameter entirely, and does not state that exactly one of walletAddress or entity_id must be provided (despite the schema noting this). The internal contradiction about markdown vs JSON also leaves the behavior unclear. Given the tool's complexity and the lack of annotation support, the description is incomplete and would mislead an agent.

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

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

The description adds meaning to modes and the walletAddress/entity_id distinction, but it omits the required 'request' wrapper parameter entirely. Examples show direct objects like {'walletAddress': '...'}, while the schema requires {'request': {...}}. It also uses inconsistent property names ('walletAddress' in the description vs 'wallet_address' in the schema's description), causing confusion. Schema coverage is 0%, so the description must compensate but instead introduces critical inaccuracies.

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: 'Get comprehensive portfolio overview for a wallet address or entity.' It also specifies distinct modes (wallet_balances, defi, hyperliquid, etc.), which differentiates it from sibling tools by showing it can focus on specific portfolio aspects. The verb 'Get' and resource 'portfolio overview' are specific and actionable.

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

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

The description provides clear usage context by explaining each mode and what it returns (e.g., 'fast-mode-default' with balances + Hyperliquid positions, 'defi' with only DeFi positions). It also distinguishes entity behavior ('only on-chain token balances'). However, it does not explicitly say when to use this tool instead of a sibling or provide when-not-to-use guidance, so it stops short of a 5.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It openly states that only special connections are included, that the tool does not return all related addresses, and explains the exchange withdrawal nuance. This is substantial, honest context about the tool's behavior and 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 efficient and front-loaded with the core action. It includes necessary caveats and an alternative tool reference without excessive verbosity. Minor typos ('the the') and slightly awkward phrasing reduce the polish, but overall sentence structure is clear and each sentence earns its place.

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

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

Given that an output schema exists (so return format need not be explained), the description is highly complete. It explains the exact meaning of 'related addresses' via the connection list, covers edge cases (exchange withdrawal addresses), and directs to the appropriate alternative tool. This provides a full mental model for the user.

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 'request' object and its fields (address, chain). The description does not add additional parameter-specific semantics, but the high schema coverage means the baseline of 3 is appropriate. The description focuses on tool behavior rather than parameter syntax.

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: 'Get information about related addresses of an input address.' It further defines 'related' by listing specific special connections, which distinguishes it from sibling tools like address_counterparties and address_transactions. The first sentence is 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 provides explicit usage guidance: it directs the user to also check 'address counterparties' for related wallets, clarifies the limited scope of special connections, and warns about the exchange withdrawal address caveat. This tells the user when to use this tool versus alternatives and what to expect from results.

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. It adds useful context about the recency limit ('20 MOST RECENT') and date-range filtering, but it does not disclose pagination mechanics, default behavior for omitted dateRange, or any potential caveats like rate limits or data freshness.

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 at two sentences and front-loads the core purpose ('Get list of 20 MOST RECENT transactions'). Every phrase adds meaningful information without redundancy.

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

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

An output schema is provided, so return-value details are not needed. However, for a tool with a single 'request' object parameter and no annotations, the description is thin: it leaves 'page' defaults, chain selection, and spam filtering unexplained. It is adequate for a simple list tool but has gaps an agent would need to resolve from the schema.

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

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

Since schema description coverage is 0%, the description must compensate. It mentions 'address' and 'date range' indirectly, but it does not explain the 'page', 'chain', or 'hideSpamToken' parameters. The schema itself contains some property descriptions, but the description fails to cover the request object's structure and leaves the agent dependent on the schema for meaning.

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

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

The description uses a specific verb ('Get') and identifies the exact resource ('list of 20 MOST RECENT transactions made by an address'). It also includes scope ('per page') and a distinguishing constraint ('Only the latest transactions according to the date range are returned'), which differentiates it from sibling tools like address_dex_trades or address_counterparties.

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 fetching an address's recent transactions but does not explicitly state when to choose this tool over alternatives or mention exclusions. The statement about date range provides a constraint but no comparative guidance.

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

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

No annotations are provided, so the description carries the burden. It discloses key behavioral traits: no NFT support, ability to search by name/symbol/address, returned data types (price, volume, contract, chain, market cap, supply), and domain resolution. It does not mention rate limits or pagination, but it covers the most important limitations and capabilities.

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

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

The description is well-organized with a clear opening statement, concise exclusions, and a bulleted list of capabilities. It is somewhat lengthy but every sentence serves a purpose, and the front-loaded 'FIRST entry point' immediately orients the 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?

The tool is a general search with 4 parameters and an output schema, so return values are covered by the schema. The description thoroughly covers when to use it, what it can/cannot do, and key parameter constraints. It is sufficient for an agent to select and invoke this tool correctly in most scenarios.

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 baseline is 3. The description adds critical cross-parameter guidance: 'DO NOT include chain name here' for query and 'ALWAYS use this parameter instead of adding chain name to the query string' for chain. This goes beyond the schema and prevents common invocation errors.

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

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

Description clearly states the tool is a general search entry point for tokens, entities, and addresses, with specific verbs like 'look up' and 'search'. It explicitly distinguishes itself from sibling tools by excluding prediction markets and NFTs, and names the alternative tool for prediction markets.

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

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

Explicitly identifies itself as the 'FIRST entry point' for lookups, provides a clear exclusion ('Do NOT use this tool for prediction markets'), and points to a specific alternative (`prediction_market_lookup`). Also advises checking token queries even for potential NFTs, giving practical when-to-use guidance.

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

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

No annotations are provided, and the description only restates the function without disclosing behavioral traits such as pagination, data freshness, or whether the result is sorted. It adds no transparency beyond the basic purpose.

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 immediately conveys the tool's purpose and key metrics. There is no wasted wording 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?

The tool is simple, has a fully described input schema, and benefits from an output schema (not shown in detail). The description sufficiently explains the core function, though it lacks usage guidance. For this complexity level, it is nearly 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 coverage is 100%, and both chain_type and time_frame have clear descriptions and enums. The description adds no additional parameter meaning, so the baseline 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 'Get chain growth rankings by active addresses, transactions, gas fees and DEX volume,' which is a specific verb+resource with detailed metrics. This distinguishes it from sibling tools focused on addresses, tokens, and prediction markets.

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. While siblings are mostly address/token-focused, the description does not explicitly mention exclusions or alternative choices.

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 disclosure burden. It explains the return format (markdown), lists columns, and mentions sorting/filtering options, but omits details like pagination behavior, date token semantics, and any potential rate limits or access requirements. It adds some value beyond the schema but leaves notable 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 well-organized with clear sections (Returns, Columns, Sorting/Filtering, Example, Notes). It is concise, front-loaded, and every section serves a purpose without redundancy.

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

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

The description is mostly complete for a leaderboard retrieval tool: it covers the purpose, output columns, filtering/sorting options, and provides an illustrative example. It omits pagination and date token details, but the output schema and schema descriptions fill in some gaps. Overall, it gives sufficient context for an agent to use the tool effectively.

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

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

Schema description coverage is 0%, so the description must compensate. It provides a concrete example using date, accountValue, totalPnl, order_by, and orderByDirection, and lists sortable/filterable fields. However, it does not explain date token formats, the page parameter, or full range semantics. The schema itself has detailed descriptions, so this is adequate but not outstanding.

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 ('Get') plus a precise resource ('Hyperliquid perpetual futures trader leaderboard') with scope ('perpetual futures only'). It distinguishes itself from sibling leaderboard tools by naming the exact platform and asset class.

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 Hyperliquid data with the 'Hyperliquid-specific endpoint' note, but it does not explicitly mention when to use this instead of alternative leaderboard tools like prediction_market_pnl_leaderboard or token_pnl_leaderboard. 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?

No annotations are provided, so the description bears the full burden. It discloses batch data updates, pre-filtering threshold (performance_score >= 15), scoring ranges, risk score meaning, return format (markdown), and dynamic inclusion of indicator columns. It does not mention rate limits or pagination, but for a read-only recommendation tool, the key behavioral traits are covered.

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

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

The description is longer than average but well-structured with clear sections (when to use, comparison, scoring, return format). It front-loads the core purpose and avoids fluff, though the repeated instructions about explaining thresholds to users could be seen as slightly 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 complexity of the scoring system and sibling differentiation, the description covers most relevant context: usage scenarios, scoring ranges, buy threshold, return fields, and dynamic columns. The key gap is parameter documentation, but for a tool that can be called without arguments, it's largely 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 description never explains the required 'request' parameter or the optional 'marketCapGroup' filter. Schema description coverage is 0%, so the description was expected to compensate, but it provides zero parameter semantics beyond the tool's general purpose. The agent would not know how to pass filters from the description alone.

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

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

The description opens with a specific verb and resource ('Discover and filter a daily list of attractive tokens'), and immediately distinguishes itself from sibling tools by explaining it uses Nansen Score Indicators to produce buy recommendations. It clearly differentiates from token_quant_scores and token_discovery_screener.

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?

Includes explicit 'Use this tool when...' guidance, plus a dedicated comparison section with token_discovery_screener, stating when to use each, including live data vs batch updates and predefined criteria. This far exceeds the minimum for usage guidance.

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

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

With no annotations, the description carries the burden of behavioral disclosure. It adds important interpretative details: blank PnL fields mean unavailable data (not zero) and clarifies that position size is quantity while position value is current marked value. This goes beyond a simple statement of purpose and helps avoid misinterpretation.

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: one main sentence plus a bulleted list of key fields. It is front-loaded with the core purpose and uses structured bullets for clarity. No unnecessary words or repetitions.

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?

An output schema exists, so return format is likely covered there. However, the input schema is complex (a union type under 'request') and the description does not explain how to populate it or that pagination is available via 'page'. The description focuses on output interpretation rather than usage, leaving a notable gap for a tool with nested input options.

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

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

Schema description coverage is 0% per context, yet the description does not explain the 'request' parameter structure, which is a union type. It only mentions 'Polygon wallet' (mapping to address) but does not clarify the page parameter or how to construct the request. The description provides minimal added value over the schema's sparse parameter info.

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

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

The description clearly states it provides a 'Prediction market PnL breakdown for a Polygon wallet.' It specifies the scope (wallet-level) and distinguishes it from sibling tools like prediction_market_address_summary or prediction_market_address_trades. The key fields section further clarifies what is included.

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 tool's usage is implied by its name and description (checking address PnL), but there is no explicit guidance on when to choose this over alternatives like prediction_market_pnl_leaderboard or wallet_pnl_for_token. No exclusions or alternative mentions 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?

With no annotations, the description carries the behavioral burden. It discloses that blank PnL/ROI fields mean 'unavailable data, not zero', which is an important semantic. It also lists the key aggregate metrics, adding context about what the summary contains. It does not explicitly state the read-only nature, but that is strongly implied by 'summary metrics'.

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 with bullet sections, front-loaded purpose, and no filler. Every sentence adds value: purpose, when to use, and key field semantics. It is appropriately sized for a summary 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?

Given the tool's simplicity and the presence of an output schema, the description is largely complete: it specifies the wallet scope, key fields, and data-availability semantics. It could additionally mention pagination or address format, but the about output schema and sibling context make the current level adequate.

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

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

The description mentions 'Polygon wallet' and wallet-level metrics, which hints that the 'request' parameter should contain an address, but it does not explain the request object structure or the 'page' parameter. Schema coverage is 0% for the top-level parameter, so the description only partially compensates. The internal address description in the schema provides some meaning, but the description itself adds limited parameter-level detail.

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 phrase ('summary metrics') and identifies the resource ('a Polygon wallet'). It clearly distinguishes this tool as the wallet-level overview from siblings like prediction_market_address_pnl and prediction_market_address_trades by calling it the 'first wallet-level Polymarket tool' for a 'quick trader overview'.

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 'When to use' section explicitly states when to use the tool ('first wallet-level... quick trader overview') and that it should precede 'detailed address trades/PnL'. It does not name alternative tool IDs, but the guidance is clear enough about usage context and 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 must carry the burden. It adds useful context about key fields (Share Size, Value USD) and clarifies that value applies per row. However, it does not explicitly state read-only behavior or other operational traits beyond the 'history' implication, so transparency is moderate.

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 well-organized with 'Key fields' and 'Pitfalls' sections. Every sentence adds value, and the structure makes the key facts easy to scan. 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?

The tool has an output schema, so return format is covered. The description adds important semantics about output fields and clarifies the profitability pitfall. Missing explicit safety/read-only annotation background, but the description is adequate for a query tool with structured schema.

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

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

The description does not explain parameters, but the input schema itself contains detailed descriptions for address, page, and dateRange (including token-based date range options). The schema covers the semantics, so the description adds no extra value here. The context signal indicates 0% schema coverage, but the actual schema appears comprehensive, so a 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 'Prediction market trade history for a Polygon wallet,' specifying the resource (Polygon wallet), the action (trade history), and scope (address-level). It also distinguishes from sibling tools like prediction_market_address_pnl by noting this is for trade activity, not profitability.

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 an explicit usage note: 'Use this for wallet trade activity, not profitability.' This tells the agent when to use the tool and when to avoid it, though it does not name the alternative sibling tool directly.

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

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

With no annotations, the description carries full burden of behavioral disclosure. It explains the underlying search API, what results include (current outcome prices, last trade price, bid/ask), and establishes an explicit output rule: 'do not silently substitute a nearby market.' It also notes the behavior of includeEventMarkets regarding count display, providing rich behavioral context.

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

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

The description is well-structured with clear sections (PM building blocks, When to use, Query tips, Output rules) and uses bullets for readability. It is longer than some, but every section earns its place given the tool's complexity. Slight over-length prevents a 5.

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

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

Given the tool's complexity and the absence of annotations, the description covers all essential aspects: what the tool does, how to use it, when to use alternatives, query formatting tips, result contents, and output rules. An output schema exists to explain return values, so the description is complete for invocation and expectation-setting.

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

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

Schema description coverage is 0% for the top-level request parameter, but nested property descriptions exist. The description compensates by clarifying what 'request' can be (name, topic, URL, slug), explaining queryVariant as a 'cleaner short keyword version', and describing includeEventMarkets's effect. It does not mention page, status, maxCandidates, or maxEventMarkets, but the schema covers those, so the added value is meaningful.

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, specific statement: 'Search Polymarket for events and markets by name, topic, URL, or slug.' It defines events vs. markets and distinguishes itself from siblings by explicitly warning against general_search and referencing prediction_market_ohlcv for price history. This fully clarifies its unique purpose.

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

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

Gives explicit when-to-use guidance: 'First tool when the user asks about a specific PM topic, event, slug, or Polymarket URL but does not provide marketId.' Also provides exclusions and alternatives: 'Do NOT use general_search for prediction markets' and 'For price history or dated moves, still use prediction_market_ohlcv.' This is exemplary.

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 each response is for one exact marketId, warns against mixing dates/prices across markets, and instructs to say so directly if no candles are returned. It also explains the complementary nature of Yes/No shares in binary markets. These are meaningful behavioral traits beyond the bare input schema, though it does not cover rate limits or auth.

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 with clear headings (When to use, Key fields, Pitfalls, Prerequisites). It leads with a concise one-line summary and each sentence adds distinct value. 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?

The description covers key data interpretation (Close price, binary complement), common pitfalls, and prerequisites. An output schema exists, so it need not detail return structure. It could mention pagination or ordering behavior, but these are in the input schema. Given the tool's moderate complexity and no annotations, the description is sufficiently 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 coverage is 0% for top-level parameters, and the description adds some meaning by clarifying that marketId is for one exact market and referencing a 'requested window.' It does not explain dateRange tokens, orderBy, or pagination, but those are already described within the nested schema. Thus the description offers modest added value, but is not fully compensating for the low top-level 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 it provides 'Historical odds/volume candles for a Polymarket market' and elaborates with 'price history and recent probability changes.' It is specific about the resource (Polymarket market) and the action (loading historical OHLCV), and the mention of 'specific market' alongside the prerequisite to lookup differentiates it from sibling tools like trades or orderbook.

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 'When to use' section identifies clear scenarios (current odds, price history, probability changes). The 'Prerequisites' section explicitly directs to call prediction_market_lookup when marketId is unknown, providing alternative guidance. However, it does not explicitly state when not to use this tool or contrast it with alternatives like prediction_market_trades, so it lacks full exclusionary guidance.

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

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

With no annotations provided, the description carries the full burden. It discloses critical behavioral nuances: order size is share quantity, No/Yes price complementarity, and how to interpret No bids as resistance rather than support. It does not mention pagination or update frequency, but the core interpretation pitfalls are thoroughly covered.

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 organized into clear sections (When to use, Key fields, Yes/No relationship, Pitfalls, Prerequisites). Every section adds critical information with no filler, and the most important caveats are front-loaded after the opening sentence.

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

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

Given the complexity of prediction market orderbooks and the presence of an output schema, the description provides rich interpretive context and clear guidance on parameter prerequisites and alternatives. It is complete enough for an agent to correctly select and invoke the tool.

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

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

Schema description coverage is 0% for the top-level 'request' parameter, but the nested schema describes marketId and page. The description adds prerequisite context for obtaining marketId via prediction_market_lookup, but does not explain the request wrapper or page parameter, so it only partially compensates.

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

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

The description clearly identifies the tool as 'Live orderbook for a Polymarket market', and the title reinforces 'Checking prediction market orderbook'. It distinguishes itself from siblings by specifying bid/ask depth, liquidity, and yes/no order structure, and explicitly contrasts with prediction_market_ohlcv.

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

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

Provides an explicit 'When to use' section listing use cases, a 'Pitfalls' section stating when NOT to use it (prefer prediction_market_ohlcv), and a 'Prerequisites' directive to call prediction_market_lookup if marketId is unknown. This is exactly the kind of alternative guidance expected.

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 adds valuable behavioral context: the 'Side Held' field reflects current side exposure where available, and if PnL fields are blank, the agent should say profitability is unavailable rather than substituting top holders or position size. It doesn't cover all behaviors (e.g., pagination, data freshness) but provides meaningful guidance beyond a simple operation description.

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 well-structured with bold headers for 'When to use', 'Key fields', 'Pitfalls', and 'Prerequisites'. It front-loads the core statement and uses bullets for clarity, with no unnecessary words.

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

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

The description covers purpose, usage scope, pitfalls, and prerequisites, and the output schema handles return values. However, the request parameter is underspecified, and with no annotations, the description is the only source of behavioral transparency. This leaves a notable gap for a tool with a nested input object.

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 for the top-level 'request' parameter is 0%, and the description only mentions marketId in the prerequisite. It does not explain the request object structure, the page parameter, or how to format the request. The nested schema has descriptions, but the description itself fails to compensate for the low 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 'PnL leaderboard for a Polymarket market' and the title says 'Checking prediction market PnL leaders'. It identifies a specific resource (Polymarket market) and operation (viewing PnL leaderboard), distinguishing it from siblings like prediction_market_top_holders and token_pnl_leaderboard.

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 includes an explicit 'When to use' section stating 'Only for profitability claims' and a prerequisite to call prediction_market_lookup if marketId is unknown. This provides clear context, but it doesn't explicitly name alternative tools or state when not to use beyond the profitability scope.

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

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

With no annotations, the description carries full burden and excels. It discloses critical field semantics: 'Position Value USD is current marked value, not final payout at resolution' and 'Cost Basis USD and Unrealized PnL USD apply to the displayed row only — not the wallet's total PM activity.' This prevents misinterpretation and goes beyond generic descriptions.

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, with a purpose statement, a bullet list of key fields, and a prerequisites section. Every sentence adds value, and the most important context is front-loaded.

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

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

The output schema reduces the burden for return values, and the description covers output field semantics well. However, the input structure is left ambiguous: it does not state whether the position is for the authenticated user or an address, and the marketId acquisition is inconsistent (the schema says prediction_market_screener, the description says prediction_market_lookup). This leaves gaps in what the API expects.

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

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

Schema description coverage is 0% for the top-level parameter, and the description does not explain the `request` object or its fields at all. The only parameter-related guidance is the prerequisite to call prediction_market_lookup, but it does not describe how to construct a valid request or what `marketId` should look like. The schema itself has nested descriptions, but the description adds little beyond that.

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 'Detailed position breakdown for a Polymarket market,' which specifies the verb (breakdown) and the resource (position in a Polymarket market). It distinguishes from sibling tools like prediction_market_orderbook and prediction_market_address_pnl, though it does not clarify whose position (e.g., the authenticated user) is returned, preventing a perfect score.

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 an explicit prerequisite: 'If marketId is unknown, call prediction_market_lookup first.' This gives clear when-to-use context and points to a sibling tool. However, it does not explicitly state when not to use this tool versus other position-related tools, such as prediction_market_address_pnl.

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 carries the full burden. It discloses literal-style matching, no fuzzy search, no bundling of unrelated topics, no inventing nearest matches, and output rules for superlatives, which are essential behavioral traits.

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

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

Front-loaded with a clear purpose, then organized into sections with bold headers. While longer than minimal, every section contributes operational value with no filler.

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

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

Covers when to use, query construction, output rules, and error handling. The output schema covers return structure, and the sibling differentiation is clear. Adequate for a complex discovery 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 top-level schema has 0% description coverage, but the description adds practical query semantics (prefer one short topic, avoid unrelated bundles) that complement the schema's nested field descriptions. It does not detail mode/status/orderBy, but these are documented 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 states 'Browse and sort Polymarket markets, events, or categories' with a specific verb and resources, and explicitly differentiates from prediction_market_lookup for resolving a single named market. This distinguishes it from 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?

Provides explicit 'When to use' and 'Do NOT use' guidance, naming the alternative tool for resolving a single market. Query tips further clarify how to structure queries, making the intended use unmistakable.

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 carries the full burden of transparency. It explicitly explains that positions are share balances, 'Position Value USD' is marked value not resolution payout, and that output is based on shown rows only. It also warns against inferring risk or smart money without explicit support. However, it does not mention pagination behavior or rate limits.

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

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

The description is front-loaded with a one-sentence summary, then uses concise bullet lists for key fields and pitfalls. It is longer than average, but each bullet adds meaningful interpretive guidance with no filler.

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

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

An output schema exists, so return-value details are not required in the description. The description covers important interpretation pitfalls and prerequisites, but it does not clarify pagination behavior or the scope of rows returned despite the page parameter, leaving a minor completeness gap.

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

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

Schema description coverage is 0%, and the description only references marketId in the prerequisite. It does not explain the request wrapper, page, orderBy, or orderByDirection semantics, leaving a significant gap that the description does not compensate for.

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 'Largest current holders for a Polymarket market,' which is a specific verb+resource pair that clearly states the tool's function. It also distinguishes this from sibling tools like prediction_market_position_detail or prediction_market_pnl_leaderboard by focusing on holder lists.

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

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

The description provides a clear context: use this to see the largest current holders of a specific Polymarket market. It gives a prerequisite ('If marketId is unknown, call prediction_market_lookup first'), though it does not explicitly contrast with alternatives or state when not to use the tool.

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 key field semantics (Share Size vs Value USD, per-row value), a pitfall about large trades not indicating smart money, and warns against using OHLCV as a price override. It does not cover pagination behavior or output structure details, but the provided key fields and pitfalls add substantial value beyond the schema.

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

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

The description is well-organized with clear sections: When to use, Key fields, Pitfalls, and Prerequisites. Each section is concise and adds unique value without redundancy. The opening sentence is direct, and the use of bullets improves scannability.

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

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

The description covers prerequisites, key field interpretation, and a common pitfall, which is sufficient for the tool's complexity. An output schema exists, so return values need not be fully explained. However, it misses details about pagination limits and dateRange options, which are relevant for a trades endpoint, preventing a perfect 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 0% based on the context signal, so the description must compensate. It mentions marketId indirectly via the prerequisite but does not explain the request object structure, dateRange tokens, or page parameter. The 'Key fields' are output fields, not parameters. This leaves parameter semantics largely undocumented.

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 'Recent trades for a Polymarket market' and differentiates from related tools by emphasizing it is the source of truth for trade-tape pricing, distinguishing it from OHLCV and address-level trade tools. The verb 'recent trades' is specific and actionable.

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

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

The 'When to use' section explicitly lists use cases and includes an important exclusion (do not overwrite with OHLCV candles). It also provides a prerequisite (call prediction_market_lookup if marketId unknown). However, it does not explicitly contrast with sibling tools like orderbook or address trades, so it falls short of a perfect 5.

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

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

With no annotations provided, the description carries full responsibility for disclosing behavioral limitations. It transparently states the endpoint is Hyperliquid-only and that only recent trades are returned (no date filtering). It also details the output columns, giving the agent a clear picture of what to expect. However, it does not mention pagination behavior, rate limits, or authorization requirements, which are minor gaps for a query 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 well-structured with clear sections for the summary, notes, return columns, sorting options, and examples. It is somewhat long, but each section earns its place by adding necessary context. The use of headers and code blocks improves readability. It could be slightly more concise, but the current structure is effective.

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 moderate complexity and the presence of an output schema, the description provides a good level of completeness. It explains the data columns, sorting options, and provides examples. It does not mention pagination parameters (like 'page') despite the schema including it, and it lacks details on result limits or error conditions. Still, the overall picture is solid for an agent to understand 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?

Although the schema descriptions are extensive, the description adds value by presenting concrete examples of parameter usage, such as sorting by 'amount' with 'order_by_direction: desc' and filtering by 'action' and 'side' with 'includeSmartMoneyLabels.' It also lists available sorting fields, which complements the schema. However, not all parameters (like 'valueUsd' or 'traderAddress') are explicitly explained in the description, though they are present in the schema with descriptions.

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

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

The description begins with a specific, action-oriented statement: 'Get recent Hyperliquid perpetual futures trades from Smart Traders and Funds across all tokens.' This clearly identifies the resource (Hyperliquid perp trades), the subject (smart traders/funds), and the scope (all tokens). It also distinguishes itself from the sibling tool 'token_discovery_screener' by offering granular data versus a 'big picture view,' making its purpose unambiguous.

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

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

The description explicitly directs users to an alternative: 'For a big picture view of smart traders and funds activity across all tokens, use token_discovery_screener with traderType="sm" filter.' It also notes the tool is Hyperliquid-only and returns recent trades only with no date filtering, giving clear context for when to choose this tool over others.

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 aggregation, exclusion of certain smart money categories, per-chain support with default 'all', and the existence of filters. This provides meaningful behavior beyond the name, though it does not mention pagination or response details (output schema covers return structure).

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 function and key constraints. The first sentence packs substantial detail (aggregation, exclusions, chains, 24h change) without fluff; the second gives a practical tip. 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 description provides the essential gist, defaults, and scope for an agent to select the tool correctly. Given the complex nested request object and the presence of an output schema, it covers the core usage, though it could briefly mention pagination or the stablecoin/native token toggles. Still, it is sufficient for initial understanding.

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

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

Schema description coverage is 0%, and the description only generically references 'filters' and 'per chain' without detailing parameters like orderBy, minHolders, includeStablecoin, or includeSmartMoneyLabels. The input schema itself has detailed parameter descriptions, but the tool description adds minimal value beyond that.

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

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

The description states 'Get aggregated (not per wallet) smart trader and fund token balances and 24h change per chain' – a specific verb and resource, and explicitly excludes whales, large holders, and influencers. This clearly distinguishes it from sibling tools like smart_traders_and_funds_perp_trades and address_historical_balances.

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 clear context: it returns aggregated balances for selected chains, defaults to all supported chains, and advises 'Use filters to narrow down the results.' It does not explicitly name alternatives or when-not-to-use, but the exclusions and aggregation scope make the appropriate use case obvious.

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

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses fallback behavior for unsupported orderBy combinations, limitations for native tokens/stablecoins, page size, and that unsupported combinations silently fall back to holding_size. These are key behavioral traits that annotations would not cover, and they are described in 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 long but extremely well-structured, using headings, bullet lists, and examples. Every section serves a purpose: column lists clarify return values, sorting lists inform valid inputs, and notes prevent misuse. The front-loaded main action gives immediate clarity, and the formatting makes complex details scannable.

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

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

The description is exceptionally complete for a complex tool: it covers both modes, output columns, sorting options, filters, edge cases (SOL, native tokens, stablecoins), fallback behaviors, and four real-world examples. Since an output schema exists, the description does not need to explain return structure, but it effectively covers all operational contexts needed to 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?

Although the top-level schema coverage is 0%, the description compensates by fully explaining every parameter through examples and explicit notes. It covers mode, tokenAddress, chain, labelType, orderBy, order_by_direction, side, upnlUsd, positionValueUsd, entryPrice, includeSmartMoneyLabels, and aggregateByEntity. The examples show exact JSON structures, making parameter usage unambiguous.

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 action ('Get up to 25 top holders information for a specific token') and specifies the two modes (onchain_tokens and perps). This definitively distinguishes it from sibling tools like token_dex_trades or token_flows by focusing on holder rankings. The scope is precisely stated, making it easy to know what resource is being accessed.

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

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

Explicit usage guidance is abundant: it warns that 'smart_money' labels are not a good proxy for market view and should only be used when explicitly requested. It states that SOL in onchain_tokens mode does NOT work and instructs to use perps mode instead. It also provides mode-specific sorting restrictions and fallback behavior, clearly covering when/when-not and 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 discloses the mode-specific behavior and the native token limitation, which is useful. However, it does not mention pagination, response details, or any potential side effects, though the output schema covers return structure. Given no annotations, a score of 3 is appropriate.

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

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

The description is concise and well-structured. It opens with a clear one-line purpose, then lists modes with bold headers, and adds a critical note. Every sentence provides unique value, and the length is appropriate for the tool's complexity.

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 essential selection context (modes, native token limitation) and is sufficient for an agent to decide when to use the tool. The schema provides exhaustive parameter documentation and the output schema covers return values, so the description does not need to repeat those details. It is not a perfect 5 because it omits any mention of the required tokenAddress parameter, but the mode descriptions imply it.

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

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

Schema description coverage is 100%, so the schema fully documents each parameter. The description adds minimal parameter-specific semantics beyond the mode names and the note about native token support, which is not in the schema. Baseline is 3 for high coverage, and the description's added insight is modest, so a 3 is justified.

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: 'Get DEX trades for a specific token.' It defines two distinct modes (onchain_tokens and perps), which clarifies the resource and scope. This distinguishes it from sibling tools like address_dex_trades by focusing on token-level queries.

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

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

Provides explicit guidance for mode selection, especially the native token limitation: 'only ETH is supported among native tokens. For other native tokens (SOL, BTC, BNB, etc.), use perps mode instead.' This tells the agent when to choose perps over onchain_tokens. However, it does not explicitly compare with alternative tools like address_dex_trades, so there is room for improvement.

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

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses result caps, chain limits, Hyperliquid perp vs spot behavior, fallback defaults for unsupported filters, timeout risks, empty-string return, and the critical warning that 'priceChange' is not a valid filter. This is rich, non-obvious behavioral information.

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

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

The description is long but well-structured with clear sections (limits, Hyperliquid case, examples, filtering/sorting options) and front-loaded key constraints. Some redundancy exists between the examples and prose warnings, but overall the length is justified given the tool's complexity.

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

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

Given the tool's complexity and the lack of annotations, the description is remarkably complete. It covers result limits, chain limits, Hyperliquid-specific behavior, supported filters and sorts, return columns, defaults, and timeouts. It also specifies the exact scenario of mixed Hyperliquid/spot chains and perp-specific fields.

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

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

Schema description coverage is 0%, and the description compensates extensively. It explains filter categories, numeric ranges, sorting options, trader semantics, the Hyperliquid special case, and provides five concrete input examples. The 'CRITICAL WARNING' about priceChange adds crucial parameter guidance beyond the schema.

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

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

Description opens with 'Get comprehensive token screening data across multiple blockchain networks with advanced filtering,' which clearly identifies a specific verb, resource, and scope. It further states the tool 'helps with token discovery and finding trending tokens by combining different metrics,' distinguishing it from sibling data tools like token_ohlcv or transaction_lookup.

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 extensive usage context: max 25 results, max 5 chains, timeout warnings, and specific guidance on when traderType values should be used (e.g., 'Use "sm" ONLY when user explicitly asks for smart money'). It does not explicitly name alternatives or exclusions relative to sibling tools, but the use-case examples and warnings give clear operational guidance.

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

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

With no annotations provided, the description carries full responsibility for disclosing behavior. It thoroughly explains the native token edge case (returns perps flows with a warning), mode-specific behavior (chain auto-set to hyperliquid in perps mode), and the granularity differences. It also mentions the prominent data-source warning, which is important for interpretability.

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 with bold section headers and bullet points, making it scannable. It is somewhat longer than necessary due to repeated references to token_recent_flows_summary, but every sentence contributes meaningful information about usage, modes, or edge cases. It earns its length.

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

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

Given the tool's complexity (multiple modes, parameter interactions, native token handling, and an output schema), the description covers all essential contextual aspects: the type of data, the supported modes, the relationship to sibling tools, and critical caveats. The presence of an output schema removes the need to describe return values, and the description fills in all other knowledge gaps.

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

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

The input schema already provides 100% description coverage for all parameters, so baseline is 3. The description adds value beyond the schema by explaining the practical meaning of modes (onchain_tokens vs perps), the holder_segment smart_money caveat, and how native placeholder addresses are handled. This enriches the schema's bare parameter 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 and resource: 'Get hourly token-flow history for ONE holder segment over a date range.' It clearly distinguishes itself from the sibling token_recent_flows_summary by highlighting granularity and scope. The subsequent modes and examples reinforce the tool's purpose without ambiguity.

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 names the alternative tool (token_recent_flows_summary) and states when to use it instead: for an on-chain snapshot across ALL wallet categories. It also provides a clear caveat about holder_segment: smart_money not being a good proxy for an overall market view, advising when to use it. This is exemplary guidance.

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

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

With no annotations provided, the description carries the full burden, and it does well by disclosing return format ('Token information as markdown'), detailing the specific fields returned for each mode, and including example JSON requests. It does not cover error handling or rate limits, but for a read-only info tool, the behavioral disclosure is strong and goes beyond a simple restatement.

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

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

The description is long but efficiently structured with clear section headers (On-chain tokens mode, Perps mode, Returns, Example, Notes). Every section adds value, and the purpose is front-loaded in the first sentence. The bullet lists for fields and the JSON examples make the content scannable without wasted words.

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

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

Given the tool's complexity (two modes, many return fields), the description is remarkably complete: it explains both modes, lists all returned fields, provides usage examples, and includes notes on address formats. The presence of an output schema reduces the need to describe return values, but the description goes beyond that anyway, making it fully self-sufficient.

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

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

The schema coverage is 0% per the context signals, but the description compensates with two concrete example JSON requests showing the exact parameter names (mode, chain, tokenAddress, timeframe) and their values. The notes clarify that on-chain mode uses contract addresses while perps mode uses symbols, adding meaningful semantics beyond the bare schema. It doesn't enumerate all chain options or timeframes in the description, but the schema provides those details.

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 retrieves token information for two distinct modes: on-chain spot details and Hyperliquid perps. It explicitly names the main purpose ('Get token information') and contrasts the two modes, distinguishing it from sibling tools that focus on single data types like token_ohlcv or token_flows. The scope is precise 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 provides clear usage context by explaining the default mode (on-chain) and the perps mode, along with notes on when to use contract addresses vs symbols. However, it does not explicitly compare this tool to sibling tools or state when to prefer it over alternatives, so it lacks explicit exclusions but gives solid context for use.

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

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

Discloses automatic resolution intervals, exact column names returned, includeMarketCap behavior, and provides multiple example usages; no annotations exist, so this is thorough 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?

Well-structured with clear sections, bold callout for general_search, bullet-like lists for intervals and columns, and multiple examples; all content earns its place.

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

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

For a multi-chain OHLCV tool with auto-resolution, the description covers supported chains, syntax, intervals, return columns, optional market cap, and example requests; output schema further enriches context.

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

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

Despite 0% schema description coverage on the top-level parameter, the description explains chain and tokenAddress semantics, including Hyperliquid symbol formats and date range tokens like '7D_AGO', adding significant meaning beyond 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?

Clearly states it gets OHLCV price data for a token with automatic interval resolution, names supported chains (EVM, Solana, Hyperliquid), and explicitly differentiates from general_search by warning it is delayed/incorrect.

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

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

Explicitly instructs to use this tool over general_search for prices, provides specific guidance for Hyperliquid perps, and includes examples for various time ranges.

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 transparency burden and does so thoroughly. It discloses output format (markdown), empty string behavior, 25-result page cap, unsupported chains (hyperevm), native token limitations, default ranking, and the fact that results are never complete. This is exemplary behavioral disclosure.

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

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

The description is long but well-structured with clear sections for modes, return values, columns, sorting, filtering, examples, and notes. The first sentence front-loads the core purpose. Some redundancy and length could be trimmed, but the organization makes it navigable and information-dense.

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

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

Given the tool's complexity and absence of annotations, the description is remarkably complete: it explains modes, native token handling, returned columns, sorting/filtering options, output behavior, and important caveats. The examples make invocation straightforward for both simple and advanced use cases.

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

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

Schema description coverage is 0%, so the description must compensate. It lists all allowed sort fields, filter categories, and gives three concrete examples with parameter names like pnlUsdTotal, nofTrades, and stillHoldingBalanceRatio. However, it does not enumerate every schema parameter (e.g., nofBuys, boughtAmount, soldAmount), leaving some burden on the schema itself.

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 'Upto 25 results (per page) of trader PnL for a token,' giving a specific verb, resource, and scope. It distinguishes itself from sibling tools by focusing on leaderboard-style trader PnL rankings and explicitly covering both on-chain and perps modes.

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

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

The description provides explicit usage context: default onchain_tokens mode vs perps mode, native token caveats, sorting/filtering instructions, and the top-25 limitation with advice to choose relevant sort order. It does not explicitly compare against sibling alternatives like wallet_pnl_for_token, but the guidance is strong enough for effective tool selection.

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. It discloses important behavioral traits: not all indicators are available for every token/chain, percentile comparisons are per market cap group, and stablecoins have limitations. It also implies this is a read-only operation by using 'Get' and describing returns.

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

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

The description is long but well-structured with sections (summary, usage, returns, notes). It is front-loaded with the main purpose and uses clear formatting. Each section adds value, though the detailed return explanation is partially redundant given the existence of an output schema.

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

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

The description thoroughly covers output semantics, usage context, and limitations, but entirely omits input parameter explanations. Given the tool's complexity (nested request with anyOf) and the presence of an output schema, the description should at least mention what parameters are needed, making it incomplete.

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

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

Schema description coverage is 0%, so the description must compensate for parameter guidance. It does not mention the 'request' parameter, tokenAddress, or chain at all. The schema provides some descriptions, but the tool description adds no input semantics, leaving the complex nested request object unexplained.

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: 'Get Nansen Score Indicators for a token - quantitative risk and reward signals.' This uses a specific verb and resource, and distinguishes it from sibling tools like token_technical_indicators and nansen_score_top_tokens by focusing on risk/reward quant scores.

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 explicitly states when to use: 'Use this tool when assessing a token's risk/reward profile, evaluating buy/sell decisions, or when the user needs quantitative data to make trading decisions.' This provides clear context, though it does not name exclusions or specific 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 behavioral disclosure. It reveals aggregation over lookback periods, the meaning of positive/negative flow, supported assets (native ETH/SOL, not BTC), and the categorization of wallet segments. It does not explicitly state read-only behavior or data latency, but these are less critical for a query 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 long but well-organized with clear sections for returns, notes, and modes. It is front-loaded with the primary purpose and repeated guidance to use token_flows for granular data is slightly redundant, but the structure helps readability without excessive wordiness.

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

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

The description covers purpose, when to use, alternatives, return format, limitations (Bitcoin not supported), and modes. It does not explicitly explain how to specify the token or chain, but the schema provides that detail. For a tool with no annotations and a nested schema, this is a fairly complete description.

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

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

Schema description coverage is 0%, and the description does not explicitly mention the tokenAddress or chain parameters. However, it does add meaning by explaining modes and supported assets (native ETH/SOL in onchain mode; SOL, ETH, BTC in perps mode). The schema itself contains descriptions for mode, chain, and lookbackPeriod, partially compensating for the lack of description coverage.

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

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

The description states a specific action and scope: 'Get an on-chain flow snapshot across ALL wallet categories in one call.' It clearly distinguishes from the sibling tool token_flows by noting this is for standard lookbacks while token_flows is for granular data and specific date ranges.

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

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

Explicit guidance is provided: 'correct choice for standard lookbacks such as 1d', 'If you have SPECIFIC date ranges in mind, use `token_flows` instead', and 'DO NOT use this tool for bitcoin.' It also explains the two modes (onchain_tokens and perps), telling when each 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?

No annotations provided, so description carries full burden. It discloses computation conventions (SMA-seeded EMA, Wilder RSI/ATR, population-σ Bollinger), edge cases (n/a for insufficient history, VWAP NULL on Hyperliquid 5m-1h), output structure (snapshot header + per-indicator rows with 5-candle deltas), and 'always computed up to now' constraint.

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?

Although long, the description is well-structured with bold headers, bullets, and a dedicated example section. Each section adds unique information: indicator list, supported chains, timeframes, output format, and edge cases. No filler or tautology.

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?

Output schema exists, and description complements it with detailed output composition (snapshot header, trend deltas). Covers all relevant usage contexts: on-chain EVM/Solana, Hyperliquid perps, timeframe selection, and data-availability limits. Examples provide complete invocation patterns.

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

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

Schema coverage is 0%, so description must compensate. It explains chain, tokenAddress, and timeframe semantics in depth: Hyperliquid perp symbol mapping, timeframe default and explicit choices, plus example JSON payloads. This is far more than the bare schema.

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

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

Description opens with a specific verb+resource: 'Get a technical-analysis snapshot for a token' enumerating 7 indicator families and the data window. It explicitly distinguishes from sibling token_ohlcv by stating 'YOU MUST USE THIS for technical analysis instead of computing indicators from raw token_ohlcv candles.'

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

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

Provides explicit guidance: mandates use over token_ohlcv with rationale (more history, charting conventions), maps timeframes to analysis horizons (intraday vs swing vs long-term), and gives Hyperliquid-specific usage rules including VWAP caveat and symbol normalization. Example usage demonstrates exact parameter combinations.

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 for behavioral disclosure. It explicitly states the page size (25), default sort order, lack of native token support, and clarifies nuanced behaviors (e.g., smart money filter means 'only transfers involving profitable addresses'; transferValueUsd filters by USD value at time of transaction). It also lists return columns, giving insight into output. However, it does not mention rate limits, error conditions, or how to advance pages via the 'page' parameter, which would be additional useful behavioral 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 long but extremely well-structured: a concise opening statement, a note on unsupported tokens, a clear columns list, sorting options, multiple example code blocks, and a structured list of filters. Every section adds practical value, and the use of headers, bold text, and code blocks makes it easy to scan. It is not redundant, though the length is justified by the tool's complexity. It is therefore concise in structure, not in word count, which earns a 4.

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

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

For a complex tool with many filters and an output schema, the description is highly complete: it covers purpose, return columns, sorting, all filters with examples, and a key limitation (native tokens). It also provides practical usage tips. The only notable gap is that pagination beyond the first page is not explained (the 'page' parameter appears in the schema but not in the description), and there is no mention of error handling or edge cases like empty results. Given the overall thoroughness, this is a strong 4.

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 top-level schema parameter ('request') has no description, resulting in a schema description coverage of 0%. The tool description fully compensates by explaining all available filters in detail: fromAddress, toAddress, transferOriginCategories, onlySmartTradersAndFunds, transferValueUsd, and sorting options. It provides formats, possible values, defaults, and examples for each, adding substantial meaning beyond the raw schema. This is exemplary compensation for sparse schema documentation.

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

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

The description starts with a clear, specific statement: 'Get 25 token transfers (per page) for a specific token based on the sort order.' It names the resource (token transfers), the verb (get), pagination (25 per page), and sorting, which distinguishes it from sibling tools like token_dex_trades or token_flows. The scope is explicit (for a specific token), and the unsupported native token note further refines the tool's purpose.

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

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

The description provides clear usage context, including when to use filters (e.g., 'Use fromAddress/toAddress when looking for a specific wallet's transfers') and what each filter controls. It also gives multiple examples covering different use cases (basic, smart money, DEX filter, from-address filter). However, it does not explicitly compare to sibling tools or state when not to use this tool, so it stops short of the explicit alternative guidance needed for 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 fully carries the burden and does well. It discloses return format (markdown), empty-string behavior, aggregation over time range, DEX-only scope, and filtering semantics. This goes beyond basic schema information and gives the agent a clear picture of what to expect.

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 with sections for Returns, Columns, Sorting Options, and Notes. It's a bit long but every section adds useful information. The main purpose is front-loaded in the first sentence.

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 is fairly comprehensive given the tool's complexity, covering purpose, behavior, return columns, sorting, and notes. It is let down by the sorting-field discrepancy and missing parameter explanations, but overall it provides enough context for an agent to invoke the tool correctly in most cases.

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

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

The description mentions buy_or_sell meaning and sorting, but it incorrectly says sorting is by 'bought_volume_usd' or 'sold_volume_usd' while the schema's orderBy enum actually uses 'token_trade_volume', 'bought_token_volume', and 'sold_token_volume'. It also does not explain key parameters like page, time_range, include_labels, or min_trade_volume_usd, with schema coverage at 0%.

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 'Get TOTAL amount of tokens bought/sold by address for a token on DEX', specifying the verb, resource, and scope. It distinguishes from siblings like token_dex_trades (individual trades) and token_current_top_holders (holders) by focusing on aggregated address-level activity on DEX only.

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

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

The description explicitly says 'Use this tool to find out WHO is buying or selling a token (on DEX) AND then you can check if they are liquidating profits or accumulating more.' This provides clear context for when to use it, though it does not explicitly mention alternatives or exclusions beyond the DEX-only scope.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'Get' which implies a read operation, but does not confirm safety, mention rate limits, authentication, error handling, or any side effects. The behavior remains opaque.

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

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

The description is a single sentence with no filler words, making it concise and front-loaded. However, it lacks any structured detail such as parameter examples or usage context, which slightly diminishes its effectiveness but does not add unnecessary length.

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?

Even though an output schema exists, the description is insufficient for confident invocation. With no annotations and 0% parameter documentation, the behavior of 'chain' and the exact scope of 'comprehensive' are undefined, and there is no differentiation from related 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 coverage is 0% and the description does not mention the parameters 'chain' or 'transaction_hash' at all. An agent has no information about the meaning, format, or default behavior of the 'chain' parameter, and the required 'transaction_hash' is only identifiable by its name.

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

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

The description states 'Get comprehensive transaction details including token transfers,' which uses a specific verb and resource. It clearly identifies the tool's purpose and the inclusion of token transfers distinguishes it from generic transaction listings, though it does not explicitly compare to sibling tools.

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

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

The description provides no context for when to use this tool versus alternatives such as address_transactions or token_transfers. There is no guidance on prerequisites, exclusions, or typical use cases, leaving the agent without direction on selecting 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?

No annotations are provided, so the description carries the full burden. While 'Get' implies a read operation, the description does not disclose return format, error behavior, or the distinction between realized/unrealized PnL. It also does not mention that the tool is non-mutating or that it may have chain defaults.

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 no fluff. Every word adds value, making it highly efficient.

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

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

The tool has a complex input schema (union type with nested fields) and an output schema exists. The description states the core purpose but does not clarify the request structure, chain default, or the role of showRealized. Given the available schema and output schema, it is minimally adequate but leaves gaps in how to 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 0% because the top-level 'request' parameter lacks a description. The tool description only mentions 'input address', 'specific token', and 'date range', covering some but not all fields (showRealized, chain). It does not explain how to structure the request object, leaving the agent to infer from the schema alone.

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

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

The description clearly states the verb ('Get'), the resource ('PnL stats for a specific token'), and the scope (address and date range). It effectively distinguishes from sibling tools like wallet_pnl_summary (wallet-level PnL) and token_pnl_leaderboard (token-level across 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 a clear context: 'Use this tool for analysing the performance of the wallet for the specific token over a time period.' This tells the agent when to apply it, though it does not explicitly mention alternatives or 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 key behavioral nuances: Hyperliquid perp includes realized plus unrealized snapshot, EVM/all reports separate sections and never sums, and named chains report realized PnL only. This goes beyond the obvious read-only nature and helps set expectations, though exact output fields are left to the output schema.

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

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

The description is five sentences long, with the main point up front and chain-specific rules logically grouped. Every sentence adds value, though the final sentence is mildly redundant with the first. Still, it is well-organized and appropriately sized for the tool's complexity.

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 an output schema, so return values are covered separately. The description addresses the main decision points (which chain to query, what to expect for each), making it complete enough for an agent to invoke correctly. It omits edge cases like invalid addresses or unsupported chains, but these are not critical for successful use.

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

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

The description adds significant meaning to the 'chain' parameter by detailing its behavioral implications ('chain='hyperliquid'' vs 'chain='all'/'evm''). However, it does not elaborate on walletAddress or dateRange beyond 'input address' and 'over a time period', leaving those semantics to the schema. With schema coverage indicated at 0%, this is a partial but incomplete compensation.

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

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

The description clearly states the tool's primary function: 'Get aggregate stats of overall realized PnL for the input address.' This specific verb+resource combination distinguishes it from siblings like wallet_pnl_for_token, which targets token-specific PnL. The chain-specific behavior is also summarized, further clarifying scope.

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 usage context: 'Use this tool for analysing the performance of the wallet over a time period.' It also explains how chain choices affect results, helping the agent decide which chain to pass. It does not name alternative tools explicitly, but the timing and scope guidance are clear.

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