Gate Info MCP

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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description reinforces this with 'Read-only public data' while adding operational context: the optional chain 'disambiguates address clashes' and the response 'returns matching rows with basic project fields.' The 'not investment advice' disclaimer adds extra context beyond the structured annotations, and there is no contradiction.

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

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

Three sentences with zero waste; the core purpose is front-loaded in the first sentence, and each subsequent sentence contributes new information (disambiguation behavior, return content, safety disclaimer). Every sentence earns its place.

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

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

For a read-only lookup tool, the description covers purpose, lookup keys, clash-disambiguation behavior, and the nature of returns, while the 100%-coverage schema handles all parameter semantics and the output schema covers return shape. The only minor omission is explicit error/limit behavior, but the schema already documents over-limit rejection.

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

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

Schema description coverage is 100%, so the baseline of 3 applies — every parameter (query, size, chain, scope, fields, query_type) is already documented with defaults, enums, and constraints. The description adds modest value by mapping query_type modes to real-world lookup keys (ticker, name, contract address, Gate symbol), but it does not materially extend the schema's parameter documentation.

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

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

States a specific verb and resource ('Look up one cryptocurrency profile') and enumerates the accepted lookup keys (ticker, name, contract address, Gate symbol). The singular 'one profile' and identifier-based framing distinguish it from siblings like info_coin_search_coins and info_coin_get_coin_rankings 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 implies the tool is for targeted single-record lookups when an identifier is already known ('by ticker, name, contract address, or Gate symbol'), and the chain parameter guidance hints at the address-disambiguation case. However, it never explicitly names alternatives such as info_coin_search_coins or states when not to use this tool, leaving routing to inference.

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

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

Annotations already mark the tool as read-only, idempotent, open-world, and non-destructive. The description adds useful context by stating 'Read-only public research data', 'No account access', 'No order placement or fund transfers', and 'Not investment advice', which goes beyond the annotation flags without contradicting them.

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

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

The description is highly compact, using terse bullet-style clauses and arrows to convey board types, parameter constraints, tool alternatives, and safety caveats. No unnecessary words or redundant elaboration are present.

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 is provided, the description covers the essential context: purpose, board categories, parameter restrictions, alternative tools, and behavioral boundaries. Nothing needed for correct invocation is missing.

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

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

The schema already provides 100% parameter description coverage, including enum-like values for ranking_type and conditional notes for time_range and new_listing-specific fields. The description mostly repeats those constraints, so it adds little semantic value beyond the schema.

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

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

The title 'Get Coin Rankings' and the enumerated board types clearly indicate the tool returns ranking lists, and the 'Single match→get_coin_info' / 'Filtered list→search_coins' lines distinguish it from sibling tools. However, the description never directly states 'retrieves ranked coin lists', relying on implication rather than an explicit purpose statement.

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 when to use this tool versus alternatives: 'Single match→get_coin_info' and 'Filtered list→search_coins'. It also gives parameter usage guidance ('time_range only for gainers/losers'), making the selection and invocation conditions clear.

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?

While annotations already mark this as read-only and non-destructive, the description adds useful behavioral context: it is public research data, involves no account access, no order placement, and no fund transfers. This goes beyond the annotation hints without contradicting them.

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

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

The description is compact and front-loaded with the main purpose in the first sentence. Every sentence adds distinct information, and there is no redundant or filler content.

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

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

Given the rich schema and read-only annotations, the description provides sufficient context: it names alternatives, states side-effect-free behavior, and clarifies non-investment-advice status. No critical context appears missing for a list-search tool.

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

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

The schema provides complete descriptions for all 8 parameters, including defaults and matching behavior, so the description adds little beyond mapping the high-level filter concepts (category, chain, cap, type) to the parameter set. Baseline 3 is appropriate since schema coverage is 100%.

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 purpose: returning a multi-row asset list filterable by category, chain, cap, and type. It also distinguishes siblings by directing one clear match to get_coin_info and board-style results to get_coin_rankings, making the tool's role clear.

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

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

It explicitly names alternative tools and the conditions for using them ('One clear match→get_coin_info. Boards→get_coin_rankings.'), giving direct when-to-use/not-use guidance. The read-only and no-order caveats also clarify appropriate usage.

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

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

Description adds meaningful safety and limitation context beyond annotations: it states read-only public research data, no account access, no order placement or fund transfers, and that results are not a security guarantee or investment advice. These align with and reinforce the readOnly and non-destructive annotations.

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

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

The description is front-loaded with the core purpose and remains relatively compact. It uses concise shorthand and arrows for relationships, though some caveats are repeated and the 'Token xor address with chain' phrasing is slightly awkward. Overall it is efficient and 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?

Given the output schema exists and all parameters are documented, the description provides enough context: purpose, selection rules, safety characteristics, and a clear alternative for on-chain stats. The limitations and read-only nature are also covered, making it complete for an agent to decide when and how to invoke 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 already covers all 5 parameters with descriptions. The description adds value by clarifying the mutual exclusivity between token and address, the requirement of chain, and pointing to scope. It does not deeply explain lang, but schema coverage is high and the added constraints improve understanding.

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 it is a public heuristic token security screen with concrete examples (tax/holder-risk style signals). It distinguishes itself from on-chain activity by explicitly directing those stats to get_token_onchain, making its unique 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 provides useful usage context: it mentions token/address exclusivity, required chain, scope, and directs on-chain activity stats to a specific sibling tool. It could be more explicit about when exactly to choose this tool over others, but the alternatives and conditions are sufficiently implied.

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 annotations already indicate readOnly, idempotent, openWorld, and non-destructive behavior, and the description adds further transparency by stating there is no account access, order placement, or fund transfer involvement. It also includes a 'not investment advice' disclaimer, which goes beyond the annotations in clarifying the tool's limitations. No contradictions exist between the description and annotations.

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

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

The description is composed of four short sentences, each serving a distinct purpose: core function, sibling alternatives, data nature, and risk disclaimer. There is no redundant wording or unnecessary detail, making it both concise and well structured.

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

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

Given that an output schema is present and the input schema fully describes all optional parameters, the description provides enough context for an agent to select and call the tool correctly. It covers alternative tool selection, read-only behavior, and relevant disclaimers without needing to enumerate return fields or parameter details.

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

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

Schema descriptions already cover all five parameters at 100% coverage, including defaults, date formats, and filter semantics, so the tool description does not need to repeat them. The description only adds a general reference to a 'date window' and optional invocation, but the parameter meanings are fully conveyed by the schema. This is the appropriate baseline score given the high schema coverage.

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

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

The description states that the tool provides a filtered release calendar in a date window, clearly identifying the resource and scope. It lacks an explicit verb such as 'returns' or 'lists,' though the tool name and context make the action unambiguous. It also distinguishes itself from sibling tools by pointing to get_macro_summary and get_macro_indicator for related use cases.

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

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

The description explicitly tells the agent when to use alternatives: zero-arg dashboards should go to get_macro_summary, and indicator snapshots or series should go to get_macro_indicator. It also notes that the data is read-only public research, reinforcing appropriate usage boundaries. This leaves no ambiguity about when this tool should be selected.

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

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

Annotations already indicate readOnlyHint and idempotentHint. The description adds useful context: 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.' This goes beyond the annotations and clarifies side effects 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 compact and information-dense, using three short sentences. It avoids redundancy and each sentence adds relevant context: what the tool does, alternatives, and safety/public-data characteristics.

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

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

Given the tool has 9 parameters (only 1 required) and an output schema, the description provides enough usage boundaries and alternative routes. It mentions the two modes, the main query dimensions (country/indicator), and exclusions. It does not exhaustively explain every parameter, but the schema already covers those details.

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

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

Schema description coverage is 100% with detailed per-parameter explanations (e.g., indicator matching, aliases, country_code fallback). The tool description only adds broad context like 'country/indicator' and 'latest or series', so it does not significantly improve parameter understanding beyond the schema.

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

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

Description states 'Official macro stats: latest or series by country/indicator' with concrete examples (CPI, rates, jobs), and explicitly differentiates from sibling tools by saying 'No event feed. Calendar→get_economic_calendar. Dashboard→get_macro_summary.' This makes the tool's purpose and scope clear.

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

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

The description explicitly provides when to use this tool versus alternatives: 'No event feed. Calendar→get_economic_calendar. Dashboard→get_macro_summary.' It also clarifies the two main modes ('latest or series') and gives example indicators, so an agent can decide correctly.

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?

Beyond the readOnly and openWorld annotations, the description adds that it is public research data with no account access, no order placement or fund transfers, and not investment advice, giving extra 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 concise and well-structured, conveying key information in two sentences plus a brief disclaimer without unnecessary verbosity.

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

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

For a simple zero-argument tool, the description fully covers what it returns, how to get more specific data via other tools, and includes a relevant disclaimer, making it contextually complete.

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

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

With zero parameters, the schema is trivially complete and the description adds no parameter details, but the baseline for zero-parameter tools is 4.

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

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

The description clearly states it is a zero-argument macro dashboard providing key snapshots and upcoming releases, making its purpose specific and distinct 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?

It explicitly instructs when to use alternative tools: for filtered calendar lists use get_economic_calendar, and for indicator snapshots/series use get_macro_indicator, providing clear 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?

Annotations already declare readOnly, idempotent, and non-destructive behavior, and the description repeats the read-only aspect. It adds minimal new behavioral information, such as error cases for invalid timeframe/symbol, but does not mention rate limits or other side effects.

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

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

The description is front-loaded with the core purpose and is fairly compact, though it redundantly repeats read-only and re-lists enums already in the schema. It remains focused and free of excessive 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?

Input constraints, defaults, and the basics of returned candle fields are covered. Since an output schema exists, the absence of a detailed return format is acceptable. Error behavior is partially mentioned, making the context reasonably complete.

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

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

The schema description coverage is 100%, with each parameter documented. The tool description adds little beyond repeating schema details, apart from clarifying default behavior for missing time range, but this is already present in parameter 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 identifies the resource (candlesticks for a trading pair/contract) and the operation (retrieving kline data). It distinguishes this tool from sibling order book and recent trades tools by naming the specific data type.

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 explicit guidance is given for when to choose this tool over the sibling kline tool or other market data tools. The description focuses on inputs and defaults but does not clarify use cases 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?

Annotations already carry readOnly/idempotent/destructive flags, and the description adds non-redundant behavioral specifics: one normalized book snapshot, over-limit depth rejected, no account access, and no order placement. This exceeds what the annotations alone communicate.

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 the main purpose but becomes repetitive: 'Read-only' appears twice, order-placement caution appears twice, and the compliance disclaimers extend the text without adding new operational meaning.

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 a full input schema, output schema, and read-only annotations, the description supplies all practical calling context: required symbol, market types, depth limits, settle usage, returned snapshot shape, and security boundaries. Nothing essential is missing.

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

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

Schema coverage is 100%, but the description still adds value by summarizing required symbol, market_type default, depth range and rejection behavior, and when settle applies (futures/delivery). This makes parameter semantics easier to absorb than reading 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 opens with a specific action and resource: reading Gate order book depth (bids/asks) for a trading pair or contract. This clearly separates it from siblings that return klines, recent trades, snapshots, or aggregate exchange metrics.

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

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

The description implies research use ('Read-only public research data') and cautions that it does not place orders, but it never explicitly states when to choose this tool over the similar-looking info_platformmetrics_get_cex_orderbook_depth or when to prefer another market-data tool. Context is present but alternatives are not named.

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

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

Annotations already mark readOnly/idempotent/non-destructive; description adds that it does not place orders, has no account access, cannot transfer funds, and rejects over-limit requests. This goes beyond structured hints and correctly warns the agent the tool cannot be used for trading.

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?

Tool is front-loaded with purpose and input summary, but the safety messaging is repetitive: 'Read-only' appears twice, and 'Does not place orders' is followed by 'no order placement'. Could be tightened without losing value.

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

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

For a read-only data tool with output schema present, it covers inputs, defaults, constraints, return content, and safety. Missing nothing an agent needs to call it correctly.

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

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

Schema coverage is 100%, so baseline 3. Description summarizes symbol, market_type, limit, and settle and adds the 'settle for futures/delivery' condition, but mostly restates schema details rather than adding new 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?

States a specific verb and resource: 'recent Gate trade prints for a trading pair or contract'. It also specifies market types and that it returns newest trades with UTC times, clearly separating it from kline/orderbook siblings.

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

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

Describes the data scope and conditions: required symbol, market_type, limit, settle for futures/delivery, and repeatedly frames it as read-only public research data. It does not explicitly name sibling tools or when to prefer kline/orderbook, but context makes selection clear.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds valuable behavior beyond that: it explains duplicate handling, missing-symbol behavior, and explicitly disclaims account access, order placement, fund transfers, and investment advice. This is strong supplementary 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 compact and front-loads the key batch behavior. The only minor issue is redundancy: 'Read-only public market data. Read-only public research data.' are similar statements that could be merged, but the rest is efficient and purposeful.

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

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

For a batch read-only tool with a rich schema and output schema, the description covers limits, deduplication, missing symbols, relationship to single-symbol semantics, and the public research nature. Nothing essential is missing for an agent to select and invoke the tool correctly.

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

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

Schema coverage is 100%, with all parameters described in the input schema. The description adds the relation to single-symbol snapshot semantics and deduplication, but most parameter meaning is already captured in the schema. Baseline 3 is appropriate when the schema carries the load.

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: batch market snapshots for up to 20 symbols. It adds distinct behavioral details (deduplication, not_found reporting) and explicitly ties semantics to the single-symbol snapshot, making it easy to differentiate from siblings.

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

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

The description references 'Same timeframe/source/quote/scope semantics as the single-symbol snapshot,' which signals when this batch tool is appropriate versus the single-symbol sibling. It does not explicitly say 'use this for multiple symbols, use the other for one symbol,' but the context is clear and no misleading guidance is present.

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

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

Annotations already mark read-only, idempotent, and non-destructive; the description adds explicit 'read-only public research data', 'No account access, no order placement or fund transfers', and 'Not investment advice'. It also discloses the CME null-data behavior.

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

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

The description is compact and every sentence adds either scope, parameter behavior, output shape, or safety context. There is no filler or repetition.

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

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

It covers defaults, return shape, data-quality quirks, and safety context. It does not enumerate every output field, but the description is sufficient given the output schema is available.

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 covers 100% of parameters with defaults and ranges. The description adds meaningful behavior beyond the schema: non-selected channel fields are null, asset=all returns both groups, and CME may be null with data_status.

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

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

The description names a specific resource and action: BTC/ETH institutional ETF/CME/CFTC daily metrics. This clearly distinguishes it from sibling market snapshot, kline, and platform metric 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?

It states what data is returned and when quirks apply, such as CME null and data_status. Selection guidance is implicit rather than explicitly contrasting alternatives, but the context is clear.

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?

Beyond the readOnly and idempotent annotations, the description adds concrete detail that it is public market breadth data with no account access, no order placement, no fund transfers, and not investment advice. This fully discloses 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 mostly concise and structured, but slightly redundant with 'Read-only public market breadth data' and 'Read-only public research data' saying similar things. Still, it remains focused and readable.

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

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

For a simple, parameterless overview tool, the description covers what data is included, that it is read-only public information, and key limitations. It does not detail output structure, but that is not required given the simplicity and existing annotations.

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

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

The tool has no parameters and the input schema is empty, matching the baseline expectation for parameter-free tools. No additional parameter documentation is needed.

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

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

The description clearly states the tool provides a broad market overview dashboard with capitalization, volume, dominance, and sentiment metrics. It distinguishes itself by explicitly noting no symbol is required, which separates it from symbol-specific market tools.

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

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

The description implies when to use it: for broad, symbol-free market aggregate data rather than individual asset or detailed market snapshots. It does not explicitly name alternative tools but the 'no symbol required' phrasing provides practical 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?

The description discloses important runtime behavior beyond annotations: when no data exists, it returns status=not_found with empty realtime/kline/project_info. It also reinforces read-only safety with explicit exclusions like no account access and no order placement, adding context beyond readOnlyHint and destructiveHint=false.

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 the core purpose and remains mostly tight across four sentences. Slight redundancy between 'Read-only public market data' and 'Read-only public research data' is the only minor waste.

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

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

With a full output schema and complete parameter documentation, the description's addition of the not_found response contract closes a key ambiguity for an agent. The tool's single-symbol scope and safe, read-only nature are well covered.

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

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

Schema coverage is 100%, with every parameter already documented with defaults, enum values, and normalization behavior. The description only lists parameter names at a high level and adds no additional semantic detail beyond what the schema provides.

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

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

The description opens with a specific and informative definition: 'One-symbol market snapshot: realtime price, a short kline clip, and project summary.' This clearly states the tool's function and resource scope, and the 'one-symbol' framing distinguishes it from sibling tools like batch_market_snapshot and market_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 description clearly communicates the single-symbol usage context, which is the key selector among sibling tools. However, it does not explicitly name alternatives such as info_marketsnapshot_batch_market_snapshot for multi-symbol queries or state when not to use this 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?

The annotations already mark the tool as read-only, idempotent, and non-destructive, and the description reinforces this by stating 'Read-only public research data' and 'No account access, no order placement or fund transfers.' There is no contradiction with the annotations. It does not mention rate limits or error behavior, but the annotation coverage lowers the burden.

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 short but contains redundant disclaimers: 'Not trading signals or investment recommendations' and 'Not investment advice' say essentially the same thing, and 'Read-only public research data' plus 'No account access...' repeats read-only. The routing arrows are useful but add clutter. Overall it is efficient but not tightly edited.

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 output schema exists and the parameter descriptions are present, the description provides enough to invoke the tool with reasonable expectations. It does not explain the output format or pagination, but those are covered by the output schema. The routing hints to siblings aid in choosing between similar 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?

The schema descriptions cover all six parameters, including examples for indicators, formats for start_time, and a compact enum-like list for timeframe. It does not explain the relationship between start_time and end_time or default ranges, but the provided format hints are sufficient for basic use. The 'ES field names' phrasing is slightly jargon-y but the examples clarify.

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 returning historical indicator columns (RSI, MACD, MAs), and the title 'Get Indicator History' reinforces the action. It does not use a direct verb like 'returns', but the intent is unambiguous. The mention of sibling tools helps position it, though it is not necessary for 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 explicitly routes OHLCV requests to get_kline and chart-label snapshot requests to get_technical_analysis, which helps an agent choose this tool when raw indicator history is needed. It does not spell out 'use this tool when you need indicator history', but that is strongly implied. The disclaimers about non-trading advice add context but are not selection criteria.

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

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

The description adds transparency beyond the annotations with statements like 'Read-only public research data' and 'No account access, no order placement or fund transfers,' which clarify the tool's safe, read-only nature. It does not contradict the annotations.

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

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

The description is poorly structured, consisting of fragments and cryptic arrow references. It is not concise or easy to parse, reducing its clarity.

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?

Although the output schema exists, the description does not sufficiently clarify the tool's purpose or its distinction from closely related siblings, leaving gaps in context for an agent.

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

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

The schema already provides descriptions for all parameters, so the baseline is 3. The tool description only adds a brief note about 'optional indicator bundle' (matching with_indicators) and does not significantly enhance parameter understanding.

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 that the tool returns OHLCV data with optional indicators, but it does not clearly differentiate this tool from the sibling marketdetail_get_kline. The phrase 'Trend OHLCV' is ambiguous, and the references to alternative tools are cryptic.

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 hints at alternatives with arrows (e.g., 'fine intervals→marketdetail_get_kline'), but it does not explicitly state when to use this tool versus the alternatives. The guidance is implicit and not fully actionable.

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

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

Annotations already establish read-only, idempotent, open-world, and non-destructive behavior. The description adds concrete behavioral context by stating there is no account access, no order placement, no fund transfers, and that the tool is not investment advice. This goes beyond the annotations, though it does not mention rate limits or authentication details.

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

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

The description is concise and front-loaded, with each sentence serving a purpose: output summary, alternative tool routing, and safety disclaimers. There is slight redundancy in the read-only and no-account-access statements, but overall it is well structured and compact.

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, the description sufficiently covers the tool's purpose, data source, output type, related tools, and behavioral limitations. It provides enough context for an agent to decide when and how to invoke this tool without missing critical information.

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

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

The schema descriptions cover all four parameters with accepted period values and time formats, so schema coverage is 100%. The tool description does not add further parameter-specific detail, which aligns with the baseline score of 3.

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

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

The description clearly identifies the tool as returning multi-timeframe chart-derived labels such as bullish/bearish/neutral summaries, and explicitly distinguishes it from OHLCV kline data and raw indicator history. This makes the tool's purpose concrete and differentiates it from closely related siblings.

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

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

The description provides explicit routing guidance: 'OHLCV→get_kline' and 'Raw columns→get_indicator_history', while framing this tool as descriptive research rather than a price forecast. It also states the tool is not an investment recommendation, giving clear usage boundaries.

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

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

Annotations already mark the tool as read-only, idempotent, and non-destructive, and the description adds context by stating 'No account access, no order placement or fund transfers' and 'Not investment advice.' It also warns through parameter descriptions about large raw payloads not being suitable for public clients. This goes beyond the annotation baseline.

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

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

The description is compact and front-loaded with the tool's core purpose, followed by aliases, errors, and safety disclaimers. It uses a telegraphic but organized style that avoids unnecessary prose. It is a bit dense, but every sentence conveys useful information without being bloated.

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 without an output schema, the description names expected response elements such as asset_summary, token_balances, multi_chain_token_balances, labels, and risk. It also mentions possible empty sections and common error identifiers, giving an agent a reasonable picture of what to expect. A short example or more explicit response shape would improve completeness, but it is not critically missing.

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

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

Schema coverage is 100%, and the parameter descriptions go beyond simple labels by explaining defaults, filtering behavior for min_value_usd, the meaning of scope values, and the relationship between upstream_raw_mode and include_upstream_raw. The address parameter is terse but adequate. This adds meaningful value over the bare schema.

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

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

The description clearly identifies the tool as providing a wallet profile with asset summary, token balances, multi-chain balances, labels, and risk. It also distinguishes it from related on-chain tools by pointing transfers to get_address_transactions. Though it uses a telegraphic fragment rather than an explicit verb, the intent is 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 gives practical usage cues: it lists chain aliases, error cases, and explicitly routes transfer-related requests to get_address_transactions. It also states that the tool is read-only public research data, which helps an agent decide when it is appropriate. It does not exhaustively compare every sibling tool, but the guidance is sufficient.

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

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

Beyond the annotations (readOnlyHint, idempotentHint), the description discloses useful edge-case behaviors: partial_upstream_response when the upstream list is unparseable, payload-size warnings for raw modes, parameter precedence ('absolute wins over time_range'), and parameters that specific paths ignore. The description is consistent with the read-only and non-destructive annotations.

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

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

The description is dense and compact, front-loading the core idea ('Paginated transfers') and then using semicolons to pack edge cases efficiently. It wastes little space relative to the 13-parameter surface it covers, though the packed style requires careful reading.

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 13 parameters and an output schema, the description covers the hardest parts: pagination, fallback behavior, chain aliases, parameter precedence, path-specific ignore rules, and payload-size warnings. It does not describe return values, but that responsibility falls to the provided output 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful semantics: mapping to explorer page_size/GET/POST paths, comparing min_value_usd semantics to get_address_info, precedence rules between start_time/end_time and time_range, and which paths ignore to_address/from_address. This goes beyond the bare 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 opens with 'Paginated transfers' and details what BTC items include, but never states the core purpose in a clear sentence like 'Get the transaction history for an on-chain address.' The intent is largely inferred from the tool name and the annotation title rather than explicitly stated in the description.

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?

Some guidance is present: chain aliases match get_address_info, upstream_raw_mode should 'prefer off for public MCP,' and include_upstream_raw is 'not for public clients.' However, there is no explicit statement of when to use this tool versus sibling tools like get_address_info or get_transaction, leaving the selection decision partially to inference.

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

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

The annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description goes beyond these by explicitly stating 'Read-only public research data' and enumerating prohibited actions (no account access, no order placement, no fund transfers). This reinforces and expands on the annotations, giving the agent a clear understanding of the tool's behavioral 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 concise and well-structured. It starts with the primary purpose, then contrasts with related tools, and ends with behavioral disclaimers. Every sentence adds value and there is no redundancy or fluff. The structure aids quick 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?

The tool has an output schema (not shown in the description), so explaining return values is not necessary. The description covers the tool's purpose, scope, and limitations, and provides enough context for an agent to decide when to use it. The only minor gap is that it does not explicitly describe typical use cases or scenarios beyond general research, but this is not critical.

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

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

The schema covers 100% of parameters with descriptive text (e.g., token symbol or contract address, scope options, upstream_raw_mode). The tool description itself does not add significant parameter-specific information beyond what is already in the schema. Baseline of 3 is appropriate given the high schema coverage, but the description adds little extra parameter semantics.

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

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

The description clearly states the tool's purpose: obtaining token on-chain data (holders, transfers, activity, smart_money). It distinguishes it from sibling tools like get_address_transactions and get_transaction by explicitly contrasting those use cases. This makes the tool's scope unambiguous and easy to differentiate.

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: it is for read-only public research data and explicitly states what it is not for (no account access, no order placement, no fund transfers). It also hints at when to use alternative tools (address ledger, single transaction). While it doesn't explicitly say 'use this tool when...', the guidance is clear enough for an agent to select appropriately.

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

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

Annotations already indicate read-only/idempotent behavior; the description adds explicit constraints such as no account access and no fund transfers, plus a sparse-fields caveat. This goes beyond the annotation baseline.

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 short and mostly focused. The 'Token view→get_token_onchain' fragment is slightly cryptic but does not make the description bloated.

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 a full output schema and complete parameter descriptions, the description is sufficient for correct invocation. It could more explicitly state when to prefer this over address-transaction tools, but that is not essential.

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

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

Schema descriptions cover 100% of parameters, so the description does not need to add much. It reinforces the hash-based lookup but does not materially enhance parameter understanding.

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 identifies retrieving a single transaction by tx_hash. The 'one transaction' wording distinguishes it from address transaction and token on-chain 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 useful context: read-only public research data, no account access, no order placement, and not investment advice. It does not explicitly compare against all sibling tools, but the token view pointer gives some direction.

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

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

Annotations already mark it read-only/idempotent/non-destructive, and the description reinforces this with 'Read-only public research data' and 'No account access, no order placement or fund transfers.' It also adds a useful 'Not investment advice' caveat. No contradiction.

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 short and front-loaded with the core purpose, but the sentence 'Cross-sector dashboard across DeFi, spot, perp, stablecoin, or bridge→get_defi_overview' is grammatically awkward and may confuse readers. The safety caveats are concise but partly redundant with annotations.

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

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

The output schema exists, so the description need not describe return values. It provides enough context about the tool's purpose, scope, and alternative dashboard tool, making it adequate for a simple read-only metrics endpoint.

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

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

Schema coverage is 100%, with clear descriptions for chain, limit, sort_by, and bridge_name, so the description does not need to add parameter detail. The description's mention of 'chain breakdown' aligns with the chain parameter but adds little beyond the schema.

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

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

The description opens with a specific purpose: 'Bridge ranking or one-bridge chain breakdown,' which clearly identifies the resource and distinguishes it from the broader DeFi/spot/perp/stablecoin dashboard tools. The phrase 'bridge→get_defi_overview' is a bit confusing but does not obscure the main 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 implies use for bridge metrics and points toward get_defi_overview for a cross-sector dashboard, but it does not explicitly state when to choose this tool over sibling bridge/chain metrics tools. Guidance is largely implicit and somewhat awkwardly worded.

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 goes beyond annotations by explicitly stating 'Read-only public research data', 'No account access', 'no order placement or fund transfers', and 'Not investment advice'. This aligns with the readOnlyHint and destructiveHint annotations, though the odd 'Gate native ladder→get_orderbook' phrase adds slight ambiguity.

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

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

The description is short and mostly to the point, but the phrase 'Gate native ladder→get_orderbook' appears extraneous and confusing. The inclusion of 'Not investment advice' is useful but could be seen as added noise.

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 output schema exists and annotations cover safety, the description adds sufficient use-case context and reinforces read-only behavior. The mentions of 'warehouse indices' and 'competitor CEX' help situate the tool, although the cryptic ladder phrase prevents 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?

The schema already provides descriptions for all five parameters, so this dimension starts at baseline. The description adds context like 'spot/perp' and 'BTC/ETH', but does not materially clarify the meanings of exchange, data_scope, or limit beyond what the schema already states.

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

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

The description clearly states the tool retrieves CEX order-book depth within ±1% for spot/perp markets and is intended for BTC/ETH liquidity benchmarking. However, the phrase 'Gate native ladder→get_orderbook' is cryptic and slightly obscures the exact 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 implies usage for competitor CEX liquidity research and explicitly notes it is read-only public data, but it does not compare with sibling tools such as info_marketdetail_get_orderbook or state when this tool should be preferred over alternatives.

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

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

Annotations already declare read-only/idempotent behavior, and the description reinforces this with 'read-only public research data' and 'no account access, no order placement or fund transfers.' It also documents edge-case responses like unsupported_granularity and not_in_scope, adding behavioral detail beyond the annotations.

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

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

The description is information-dense and front-loaded with the core purpose, but it packs many details into a single run-on paragraph with semicolons. It could be organized into cleaner structure without losing content.

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

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

Given the complex branching by metric_group, the description covers sources, fields, defaults, constraints, and special return statuses. With an output schema present, not detailing every response field is acceptable.

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?

Every parameter is described in detail, including which metric_group it applies to, defaults for start/end/lookback/chain, and special response values. This adds significant meaning beyond the bare schema fields.

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

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

Clearly states the tool returns chain-level activity metrics by metric_group and enumerates the three metric groups with their data sources. This distinguishes it from sibling platform metrics tools, even without naming them explicitly.

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 explicit guidance on when to choose this tool over sibling tools such as platform history or defi overview. It describes per-metric-group behavior but not selection criteria relative to 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?

The description adds behavioral transparency beyond the annotations by stating 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.' This clarifies safety and side-effect behavior consistent with readOnlyHint.

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 front-loaded with the main purpose. It includes necessary routing and safety information, though the multiple short sentences could be consolidated slightly without losing meaning.

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

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

Given the simple interface with one optional parameter and an existing output schema, the description provides complete context: purpose, usage, routing, and safety. Nothing critical is missing for an agent to decide when and how to invoke this tool.

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

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

The schema has 100% coverage for the single 'category' parameter with a detailed description of allowed values and handling of unknown inputs. The tool description does not add additional parameter semantics beyond the schema, so the baseline score of 3 applies.

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

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

The description clearly states the tool provides a cross-sector dashboard for DeFi, spot, perp, stablecoin, or bridge categories. It also distinguishes from sibling tools by specifying when to use get_bridge_metrics and get_platform_info, making the purpose unambiguous.

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

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

It explicitly provides routing guidelines: 'One bridge ranking or chain detail→get_bridge_metrics. One protocol→get_platform_info.' This tells the agent when to use alternative tools instead, satisfying the usage guidance requirement.

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?

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds explicit statements about read-only public research data, no account access, no order placement, and no fund transfers. It also explains conditional response behaviors (e.g., scope=full adds por, include_flows returns flows.series), which supplements the annotation hints.

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

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

The description is moderately concise but uses a list-like conditional style with several 'scope=full + ...' clauses, making it slightly verbose and harder to scan. It is not excessively long, but the structure could be improved by grouping related options more clearly.

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 main scopes, optional flags, and cross-references to a sibling tool. It clarifies the behavior of include_history (precomputed comparison fields vs raw snapshots) and event_type filtering. While it does not detail the full output schema, it provides enough context for a typical agent to understand the tool's capabilities and limitations.

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

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

The schema already covers 100% of parameter descriptions, but the main description adds semantic details not present in the schema, such as the structure of flows.series[] and events[], the distinction between raw snapshots and precomputed comparison fields for include_history, and the normalized exchange name mapping. This enhances understanding beyond 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 identifies the resource as 'Exchange reserve snapshots by venue and asset', which is specific and distinguishes it from sibling data tools. While it lacks an explicit verb like 'Get' or 'Return', the tool name itself contains 'get_exchange_reserves' and the description makes the purpose unambiguous.

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

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

The description provides a cross-reference to a sibling tool ('TVL history→get_platform_history'), giving some comparative context. However, it does not explicitly state when to prefer this tool over alternatives for exchange reserve data, leaving the usage largely implied from the title and content.

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

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

Beyond the annotations indicating read-only and non-destructive behavior, the description explicitly states 'No account access, no order placement or fund transfers' and 'Not investment advice,' providing additional context about the tool's limitations and safety profile. This goes slightly beyond the annotations but does not fully describe all behavioral aspects.

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, using only a few short sentences to convey purpose and safety disclaimers. It contains no redundant or unnecessary information, making it efficient and easy to parse.

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 the tool has an output schema (not shown here), the description does not need to explain return values. The description covers the core purpose and safety notes, providing sufficient context for an agent to understand what the tool does. It lacks some usage context but that is covered under usage guidelines.

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

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

The schema descriptions for 'symbol', 'range', and 'exchange' provide basic meaning (e.g., 'Symbol e.g. BTC, ETH'), and the tool description does not elaborate further. Since schema coverage is 100%, this meets the baseline but adds no extra semantic clarity.

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 as returning liquidation density by symbol and price buckets. It is distinct from sibling tools by explicitly focusing on liquidation heatmap data, differentiating it from other market and platform metrics 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 does not provide explicit guidance on when to use this tool versus alternatives. It does not mention potential use cases or contrast with other platform metrics tools, leaving the agent to infer appropriate usage from the tool name and description alone.

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

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

Annotations already mark read-only and idempotent. Description adds extra context: 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.' This goes beyond the annotation flags and clarifies side-effect and security implications.

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 packs essential information into a few sentences: purpose, alternatives, CEX perps handling, and read-only nature. No fluff or repetition, 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?

Given the tool's complexity (6 parameters, output schema), the description provides sufficient context: it states what the output is (time series), how to select a protocol (exchange_slug or platform_name), when to use alternatives, and emphasizes safe read-only behavior. Output schema is separately provided, so no missing critical 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?

Schema covers 100% of parameters with descriptions. The description adds nuance beyond schema: 'volume_perps returns series when present in platform_history (GAP-001)' and clarifies the exchange_slug/platform_name relationship. This enriches parameter understanding without redundancy.

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 returns daily TVL, volume, and fees time series for one named protocol, and explicitly distinguishes it from get_platform_info (profile) and search_platforms (ranked list). This leaves no ambiguity about the resource and operation.

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 says when to use this tool versus alternatives: 'One-shot profile→get_platform_info. Ranked multi-protocol list→search_platforms.' Also specifies CEX perps history requires exchange_slug or platform_name, providing clear selection criteria.

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

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

The description goes beyond annotations by stating the tool is read-only, provides public research data, involves no account access, order placement, or fund transfers, and is not investment advice. This aligns with the readOnlyHint and idempotentHint annotations and adds meaningful safety 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 brief, front-loaded with the core purpose, and uses compact separate statements for conditions and limitations. No redundant or filler wording is present.

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 schema and annotations, the description is fully sufficient. It covers the tool's purpose, parameter behavior, safety profile, and relationship to sibling tools, with no apparent missing 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?

The schema already covers 100% of parameter descriptions, so the baseline is 3. The description adds useful context by explaining the purpose of oi_symbol_limit as 'top-N OI breakdown' and clarifying scope-dependent behavior, slightly exceeding 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 tool returns a protocol profile by name and scope. It distinguishes itself from sibling tools by explicitly referencing search_platforms for ranked lists and get_platform_history for daily time series.

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

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

The description explains when to use optional parameters (scope=full, include_oi_symbol_detail=true) and provides cross-tool guidance for list and time-series needs. This gives an agent clear direction on selecting this tool over alternatives.

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

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

Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false) are reinforced by the description: 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.' This fully discloses side effects and restrictions beyond the annotations.

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

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

The description is dense but efficient, using arrows and semicolons to pack information. It could be trimmed slightly (e.g., repeating 'extension' multiple times), but it remains scannable and focused.

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 output schema exists separately and the description fully covers input semantics, behavior (sections, defaults), and limitations (depeg_events filters), an agent has all context needed to call the tool correctly without external references.

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

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

All 9 parameters are described with meaningful detail: supported values for symbol, enumeration of sections, default windows, and valid ranges (e.g., min_deviation 0.001-0.2). This adds depth beyond the schema's 100% 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?

Clearly states it provides stablecoin-only ranking or per-symbol chain breakdown. Explicitly distinguishes from broader tools by referencing get_market_overview and get_defi_overview, making its niche unmistakable.

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 direct usage guidance: 'Broad market dashboard→get_market_overview. Cross-sector rollup→get_defi_overview' points to alternatives. Also explains when sections require scope=full and notes defaults, leaving no ambiguity about when to invoke.

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 explicitly states 'Read-only public research data. No account access, no order placement or fund transfers', which aligns with the readOnlyHint annotation and adds context about data accessibility. This goes beyond the annotation's bare flag by clarifying that the tool is safe and non-destructive. No contradiction exists, so the score remains high.

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 brief but poorly structured. It mixes declarative statements with arrow notations and repeated scope hints, creating a fragmented flow. Phrases like 'scope=full adds apy_base_30d...' are placed awkwardly, and the arrows ('→') are unconventional. While concise, the lack of coherent structure undermines readability and 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?

Given the tool has 8 optional parameters and no output schema details, a self-contained description is essential. The description references sibling tools via arrows ('get_platform_info', 'get_platform_history') without explaining their relevance, and it does not define key terms like 'exposure' or clarify how 'scope' affects results. A newcomer would struggle to fully understand the tool's capabilities from this text alone.

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

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

Schema description coverage is 100%, with each parameter having a short description (e.g., 'Chain filter.', 'Rows; default 20, max 400.'). The tool description adds little beyond the schema, except a cryptic note that pool_type 'maps to ES exposure' which may confuse rather than clarify. Since the schema already carries most semantic weight, a baseline of 3 is appropriate; the description does not meaningfully enrich parameter understanding.

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 'Lending and LP pools by APY or TVL', which provides a clear verb (get) and resource (yield pools). It distinguishes the tool from siblings by its focus on yield/lending metrics, and the title 'Get Yield Pools' reinforces the purpose. However, the subsequent shorthand arrows (e.g., 'One protocol profile→get_platform_info') introduce ambiguity that slightly weakens clarity.

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 explicit guidance is given on when to use this tool versus alternatives. The description mentions 'One protocol profile→get_platform_info' and 'TVL series→get_platform_history', but these are cryptic references rather than clear conditional instructions. Users are left to infer that this tool is for current pool listings, not historical series, without any direct statement.

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 clearly states 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice,' which goes beyond the readOnly and openWorld annotations by specifying access and safety characteristics. There is no contradiction with the annotations.

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

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

The description is concise and each sentence adds information, but the arrow-phrased references ('One-shot profile→get_platform_info') are somewhat cryptic and could be more readable. Overall length is appropriate and no filler is present.

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 is present and parameters are fully covered by the schema, the description sufficiently covers purpose, behavior, and key alternative tools. It does not describe output shape, but that is not required when the output schema is available.

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

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

All five parameters are already described with 100% schema coverage, including detailed mapping for platform_type and sort_order behavior. The top-level description adds only generic 'filter and sort' context, not additional parameter-specific meaning, so it meets the baseline but does not exceed it.

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 'Ranked multi-protocol list with filter and sort,' which clearly identifies the tool as a search/list operation for platforms and distinguishes it from detail/history tools by explicitly referencing get_platform_info and get_platform_history for one-shot profile and daily series use cases.

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

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

It provides implicit usage guidance: use this tool for ranked multi-protocol lists with filter/sort, while pointing to get_platform_info for a single profile and get_platform_history for a single protocol's daily series. It could be more explicit about when to prefer this over other sibling tools, but the key alternatives are named.

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