Gate Info MCP

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description adds valuable context: 'Read-only public research data', 'No account access, no order placement or fund transfers', and 'Not investment advice'. This clarifies the tool's safety and limitations beyond the structured annotations.

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

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

The description is extremely concise, using short phrases that front-load the core purpose and key distinctions. Every clause adds value: purpose, chain disambiguation, alternatives, safety, and disclaimer. No wasted words.

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

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

Given the 6 parameters, an output schema, and rich annotations, the description covers the essential aspects: what the tool does, when to use it vs alternatives, chain handling, read-only status, and limitations. The output schema handles return-value details, so nothing critical is missing.

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

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

Schema coverage is 100%, so all 6 parameters are fully documented in the schema. The description adds extra meaning by explaining that 'Chain fixes address clashes' and that the query can be a 'ticker, name, or contract'. This goes beyond the schema's parameter descriptions and aids correct invocation.

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 'Single-target lookup: ticker, name, or contract→rows', which precisely identifies the tool's verb (lookup) and resource (coin info), and explicitly contrasts it with 'Filtered lists→search_coins' and 'Boards→get_coin_rankings'. This clearly distinguishes it from sibling tools.

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

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

The description gives explicit usage context: use this for single-target lookups, and directs users to search_coins for filtered lists and get_coin_rankings for boards. It also notes that 'Chain fixes address clashes', providing a key usage hint for address disambiguation.

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=true, idempotentHint=true, and destructiveHint=false. The description adds extra context beyond annotations by stating 'Read-only public research data', 'No account access, no order placement or fund transfers', and 'Not investment advice'. This clarifies the tool's non-transactional nature, though it doesn't detail return format or error behavior (output schema helps).

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 only three sentences, each earning its place: board types, usage constraints, and safety disclaimers. It is front-loaded with the most important info (the board categories) and avoids redundant elaboration of structured data.

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

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

Given the tool's moderate complexity with 6 parameters, the description covers the key context: board types, time_range restriction, alternatives, and safety boundaries. The output schema handles return values, so the description doesn't need to explain them. It is complete for guiding selection and invocation.

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

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

Schema coverage is 100% with all six parameters documented. The description adds a compact board listing (mirroring the ranking_type enum) and reiterates the time_range constraint from the schema, but doesn't add meaning beyond the structured field descriptions. Per guidelines, baseline 3 applies when schema covers parameters thoroughly.

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 coin rankings for various boards (popular, gainers/losers, etc.) and provides strong differentiation from sibling tools by explicitly pointing to get_coin_info for single matches and search_coins for filtered lists. The tool name and title reinforce the 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 gives explicit usage guidance: it states that time_range only applies to gainers/losers and provides alternative tools for other use cases (single match→get_coin_info, filtered list→search_coins). This clearly tells the agent when to use this tool versus 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 readOnlyHint, idempotentHint, and destructiveHint=false. The description adds valuable context beyond these: 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.' These statements clarify the operational boundaries and risk profile, which is not fully captured by the annotation booleans.

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 only three sentences and every sentence serves a purpose: the first states the core function, the second gives routing alternatives, and the third provides safety context. It is front-loaded with the most important information and contains zero filler.

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

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

For a list/search tool with 8 parameters and an output schema, the description is adequately complete. It covers the tool's scope, key routing alternatives, and relevant restrictions/safety caveats. The output schema handles return-value expectations, so the description does not need to elaborate on that. Minor omissions like pagination behavior are already documented in the schema.

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

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

Schema description coverage is 100%, so the baseline is 3. The description only restates high-level filter dimensions ('category, chain, cap, type') without adding any detail beyond the schema. It does not explain default behavior, edge cases, or relationship between parameters, so no extra value is provided.

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 'Multi-row asset list by category, chain, cap, type,' which clearly states the tool's verb, resource, and scoping dimensions. It also differentiates from siblings by explicitly routing 'One clear match→get_coin_info' and 'Boards→get_coin_rankings,' making the tool's purpose unambiguous even among many related tools.

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

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

The description provides explicit when-to-use guidance by naming alternatives: 'One clear match→get_coin_info' and 'Boards→get_coin_rankings.' This directly tells the agent when to choose the sibling tools instead. It also establishes the general context as 'Read-only public research data,' further clarifying appropriate use cases.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Read-only public research data. No account access, no order placement or fund transfers.' It also adds important caveats like 'Not a security guarantee' and 'Not investment advice,' which go beyond the annotations to set proper expectations.

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, but it repeats 'Not investment advice' twice and 'public' twice, which adds redundancy. It could be tightened by merging the caveats into a single sentence while preserving all essential information.

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

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

Given the presence of a rich output schema, comprehensive annotations, and sibling context, the description covers safety, usage, limitations, and alternatives. It is complete for the tool's complexity, providing all necessary context for an agent to select and invoke 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 parameters are well-documented. The description adds valuable semantic context by explaining the 'Token xor address with chain' relationship, which is not explicit in the schema, and points to 'scope in schema' to guide parameter usage.

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 a 'token security screen' with a concrete example ('tax/holder-risk style signals'), making the purpose specific and understandable. It also distinguishes itself from the sibling tool 'get_token_onchain' by explicitly directing on-chain activity stats to that alternative.

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

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

The description provides clear usage guidance by stating when NOT to use it (for on-chain activity stats, use get_token_onchain), and clarifies the input constraint 'Token xor address with chain.' It also notes the tool is for public research and not for investment advice, setting expectations for appropriate use.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds 'Read-only public research data,' 'No account access, no order placement or fund transfers,' and 'Not investment advice,' which enriches behavioral context beyond the annotations 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 four short sentences, each serving a distinct purpose: stating the tool's function, redirecting to alternatives, clarifying safety/access limitations, and adding a disclaimer. No wasted words.

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

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

With a comprehensive parameter schema and an output schema present, the description covers the essential context: purpose, alternatives, and safety. It does not explain return format, but the output schema implies that. Minor omission of response behavior, but not a significant gap for this simple read-only tool.

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

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

Schema description coverage is 100%, so the schema already documents each parameter. The description does not add parameter-level detail, which aligns with the baseline expectation of 3 when parameter semantics are fully covered by the schema.

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

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

The description states 'Filtered release calendar in a date window' with a specific verb, resource, and scope. It clearly differentiates from siblings by naming get_macro_summary and get_macro_indicator for related but distinct 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?

Explicitly provides when-to-use guidance: 'Zero-arg dashboard→get_macro_summary. Indicator snapshot or series→get_macro_indicator.' This gives clear alternatives and exclusion criteria, which is exactly what the dimension requires.

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=true, idempotentHint=true, and destructiveHint=false. Description adds context: 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.' This goes beyond annotations 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?

Description is compact, front-loads purpose, and every sentence provides distinct value: what it does, what it excludes, pointers to alternatives, and safety guarantees. No redundancy.

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

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

With output schema present and full schema coverage, description doesn't need to list return fields. It covers tool purpose, usage boundaries, and safety profile. The pointers to sibling tools complete the contextual picture.

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 all 9 parameters are documented. Description mentions 'latest or series' (mode) and 'by country/indicator' (country/indicator params) but adds no syntax details beyond schema. Baseline 3 applies.

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

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

Description clearly states 'Official macro stats: latest or series by country/indicator (CPI, rates, jobs)', specifying verb and resource. It distinguishes from siblings by noting 'No event feed' and pointing to get_economic_calendar and get_macro_summary.

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 directs to alternatives: 'Calendar→get_economic_calendar. Dashboard→get_macro_summary.' Also provides context that it is read-only public research data with no account access, making selection criteria 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?

Despite annotations already declaring readOnlyHint=true and openWorldHint=true, the description adds valuable context: 'Read-only public research data. No account access, no order placement or fund transfers.' This goes beyond generic read-only flags by specifying exactly what operations are excluded. It also notes 'Not investment advice' as a disclosure. No contradiction with annotations.

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

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

The description is three concise sentences: purpose, alternative routing, and behavioral constraints. It is front-loaded with the main purpose and each sentence earns its place. No redundant or vague wording; every line contributes to the tool's understanding.

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

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

For a zero-arg tool with an output schema present, the description sufficiently covers what the tool returns (key snapshots and upcoming releases), when to use alternatives, and its operational boundaries. It gives the agent enough context to decide when to invoke it without needing return-value 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?

The input schema is empty, and the description explicitly states 'Zero-arg' upfront, confirming no parameters are required. This reinforces the schema's empty object and helps the agent avoid looking for parameters. With 0 params the baseline is 4, and the description meets that baseline effectively.

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

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

The description opens with 'Zero-arg macro dashboard: key snapshots plus upcoming releases,' clearly identifying the tool's specific verb (get summary) and resource (macro dashboard). It distinguishes itself from sibling tools by explicitly noting that a filtered calendar list should use get_economic_calendar and an indicator snapshot/series should use get_macro_indicator, making the purpose 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?

The description provides explicit routing: 'Filtered calendar list→get_economic_calendar. Indicator snapshot or series→get_macro_indicator.' This tells the agent exactly when to use alternatives, which implies this tool is for the general macro dashboard without filtering or indicator-specific queries. This is strong usage guidance with clear exclusions.

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

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

Annotations already declare read-only and non-destructive behavior. The description adds valuable context: 'No account access, no order placement or fund transfers' and 'Not investment advice', which goes beyond the annotation hints and clarifies that this is purely public market data.

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: purpose first, then alternative tool, then safety disclaimers, all in a few short sentences. No wasted words.

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

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

Given the existence of a complete output schema and rich annotations, the description provides sufficient context: what data is returned, differences from related tools, prerequisites, and safety constraints. It is complete for a read-only market data 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 input schema has 100% parameter coverage with descriptions for all 8 parameters. The description does not add new parameter-level semantics beyond what the schema provides, so it relies on the schema as the baseline.

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's function: retrieving exchange pair or contract candles with fine intervals. It distinguishes itself from the sibling tool `markettrend_get_kline` by specifying which one to use for trend-index OHLCV or indicator bundles.

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 provides when-to-use guidance: use this tool for raw candles, and directs users to `markettrend_get_kline` for trend-index or indicator bundles. Also mentions a prerequisite: 'needs Gate base URL', which clarifies operational context.

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

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

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description adds useful context beyond annotations by stating 'needs base URL', 'No account access, no order placement or fund transfers', and 'Not investment advice', which clarifies operational constraints and disclaimers. No contradiction with annotations.

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

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

The description is compact and front-loaded with the core purpose, then uses brief mapping arrows to alternatives. Although the structure is slightly fragmented (jumping from alternatives to read-only to disclaimer), each sentence carries useful information without excess.

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 5 parameters, a nested object, and an output schema, the description appropriately focuses on purpose, usage boundaries, and the prerequisite of a base URL. It does not explain every parameter, but the schema already covers them, and the description adds enough operational context for a complete agent interaction.

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?

Input schema coverage is 100%, and the description does not add additional parameter-specific details beyond what the schema already provides. The 'depth' and 'market_type' parameters are described adequately in the schema, so the description adds little unique value here.

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

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

The description clearly states the tool returns an order book depth (bids/asks ladder) from Gate, which is a specific verb+resource. It also distinguishes itself from siblings by explicitly mapping trade tape to get_recent_trades and trend-index bars to markettrend_get_kline.

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

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

The description gives explicit guidance on when to use alternatives (trade tape→get_recent_trades, trend-index bars→markettrend_get_kline) and states the tool is read-only public research data with no account access or order placement, clarifying appropriate contexts. It also notes the requirement of a base URL.

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=true, idempotentHint=true, and destructiveHint=false. The description adds valuable context beyond annotations: 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.' This clearly communicates non-safety-related limitations and reinforces the read-only nature without contradicting 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 extremely concise—four short sentences that immediately state the purpose, then give alternatives, then safety/context. Every sentence carries information and there is no redundancy or fluff, making it easy for an agent to parse quickly.

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), so return structure is covered externally. The description addresses the core use case, differentiates from alternatives, describes safety/access limitations, and mentions a prerequisite ('needs base URL'). This is complete for a straightforward read-only data 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 input schema provides 100% coverage with meaningful descriptions for all five parameters (e.g., symbol, limit, settle, market_type, extra). The description does not add parameter-specific details beyond the schema, so a baseline score of 3 is appropriate given the schema handles parameter semantics.

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

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

The description clearly identifies the resource as 'Recent trade prints tape from Gate' and implicitly names the operation (get recent trades). It distinguishes from siblings by explicitly referencing get_orderbook for depth data and markettrend_get_kline for trend bars, making the tool's unique function obvious.

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 when-to-use guidance: use this for recent trade prints, get_orderbook for depth ladder, and markettrend_get_kline for trend-index bars. It also notes the need for a base URL and clarifies that this is public research data with no account access or trading capabilities, which helps set expectations.

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

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

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds valuable context: 'Read-only public research data. No account access, no order placement or fund transfers' and partial-miss tolerance. No contradiction with annotations.

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

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

The description is compact—four short sentences, zero fluff. It front-loads the core purpose and then supplies routing and safety context efficiently.

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

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

Given the rich annotations, 100% parameter coverage, and presence of an output schema, the description fully covers purpose, usage boundaries, and safety caveats. It is complete for an agent to select and invoke this tool correctly.

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

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

Schema description coverage is 100% and each parameter already has a descriptive comment (e.g., symbols max 20, missing symbols yield empty rows, source defaults). The description's batch limit and partial-miss mention add little beyond the schema, so baseline 3 is appropriate.

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

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

The description opens with 'Batch quotes up to 20 symbols', clearly specifying the verb (batch quotes), resource (market snapshots), and scope (up to 20 symbols). It also distinguishes from the single-symbol sibling get_market_snapshot.

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 routing rules: 'One symbol→get_market_snapshot. Deep trend→markettrend_get_kline. Breadth→get_market_overview.' This tells the agent exactly when to use this tool versus 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 significant behavioral detail beyond the annotations, such as nulling non-selected fields, the CME often being null with data_status 'cme_source_not_procured', and the return shape. It also reinforces the read-only and safe nature with 'No account access, no order placement or fund transfers,' which complements the readOnlyHint and destructiveHint 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 three sentences, front-loaded with the core purpose, then parameter specifics, then return and safety notes. Every sentence provides distinct value with no redundancy or filler.

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

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

Given the output schema exists, the description does not need to explain return values, but it still mentions the return structure. It covers the data source, null quirks, safety, and disclaimers, making it complete for a read-only public data tool with good annotations and full parameter coverage.

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, but the description adds extra meaning by explaining the null behavior for channels ('nulls non-selected fields') and confirming the asset/channel value sets. This nuance is not present in the schema and helps the agent anticipate field availability in responses.

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 BTC/ETH institutional ETF/CME/CFTC daily metrics, distinguishing it from other market snapshot tools. It explicitly states the data source (OpenSearch) and the return structure (assets[].latest, series[]), leaving no ambiguity about its function.

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 conveys a clear context for use: it is for institutional metrics data, publicly available and read-only. It does not explicitly name alternative tools or exclusions, but the specificity of 'institutional ETF/CME/CFTC' implies when to select this tool over siblings like market snapshot or platform metrics.

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, non-destructive behavior. The description adds valuable context: 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.' This goes beyond annotations 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, followed by clear routing to alternatives and disclaimers. Every sentence adds value, no redundancy or fluff.

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

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

For a parameterless dashboard tool with an output schema already present, the description fully covers what the tool does, what it excludes, and when to use alternatives. It is complete and self-contained.

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

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

The input schema has zero parameters, so the description correctly focuses on scope and alternatives. There are no parameter semantics to explain, and the 0-parameter baseline of 4 applies. The description does not need to mention parameters.

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

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

The description clearly states the tool provides a broad market dashboard with cap, volume, dominance, and sentiment. It explicitly excludes stablecoin ranking and lists alternatives, distinguishing it from get_stablecoin_info, get_market_snapshot, and batch_market_snapshot.

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

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

Explicit usage guidance is provided: stablecoin-only ranking or chain breakdown should use get_stablecoin_info, one asset uses get_market_snapshot, and many symbols use batch_market_snapshot. It also indicates this tool is for broad market context with no stablecoin ranking.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds context about no account access, no order placement or fund transfers, and not investment advice. This extra behavioral disclosure is valuable even though the bar is lowered due to comprehensive 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 extremely concise, using arrow notation to quickly communicate alternatives, and safely disclaims. Every word earns its place, and the structure is front-loaded with purpose followed by usage alternatives and safety notes.

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

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

With a rich output schema, full parameter documentation, and strong annotations, the description is complete for its purpose. It covers single-symbol use, distinguishes from related tools, and provides safety disclaimers—all in a compact form. No significant gaps remain.

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

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

Schema description coverage is 100%, so the baseline is 3. The description does not add meaningful parameter details beyond what the schema provides—it only mentions "One-symbol" which aligns with the symbol param. No additional compensation needed, but no extra credit either.

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 price, kline clip, and project data for a single symbol. It explicitly distinguishes from sibling tools by naming alternatives for trend, gate, batch, and breadth use cases, making its specific role 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?

It gives explicit when-to-use guidance: "One-symbol" for this tool, and then maps other scenarios to alternative tools (trend, gate, many, breadth). This is a model of clear usage 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 declare readOnlyHint, idempotentHint, and destructiveHint false, so the safety profile is well covered. The description adds meaningful context beyond annotations by specifying 'Read-only public research data. No account access, no order placement or fund transfers.' This disambiguates the tool's side effects and access requirements, which is valuable even with annotations present.

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

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

The description is extremely concise: three sentences, each adding distinct value. The primary purpose is front-loaded, followed by targeted sibling references and disclaimers. No wasted words or redundant restatements of the name.

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 historical data tool with rich annotations, a full output schema, and fully specified parameters, the description covers all necessary ground: purpose, alternatives, disclaimers, and access limitations. It does not mention return format, but the output schema handles that. Minor gap: no mention of pagination or limit behavior beyond schema, but this is not critical for a simple read operation.

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

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

Schema coverage is 100%, so parameters are fully documented in the schema. The description adds a small semantic layer by mentioning the indicator types (RSI, MACD, MAs), which helps clarify the 'indicators' parameter, but it does not go beyond what the schema already lists. This is sufficient but not exceptional; baseline 3 is appropriate.

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

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

The description clearly states the tool's function: 'Historical indicator columns (RSI, MACD, MAs)' with a specific verb implied by 'get' in the name. It explicitly differentiates from siblings by mapping OHLCV data to get_kline and chart-label snapshots to get_technical_analysis, leaving no ambiguity about scope.

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

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

Provides explicit usage alternatives: 'OHLCV→get_kline. Chart-label snapshot→get_technical_analysis.' This tells the agent when to use this tool versus the alternatives. It also clarifies that the tool does not provide trading signals or investment advice, setting clear boundaries for appropriate use.

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

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

The description adds meaningful behavioral context beyond annotations: 'Read-only public research data,' 'No account access, no order placement or fund transfers,' and 'Not investment advice.' These specifics disclose safety and operational limits that align with the readOnlyHint, openWorldHint, and destructiveHint annotations, with no contradictions.

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

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

The description is well-structured, with the main purpose first, followed by concise alternatives using arrows. It is slightly long (7 clauses) but every sentence earns its place, providing both usage guidance and safety disclaimers. The 'Not investment advice' disclaimer is arguably extra but acceptable.

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 8-parameter schema (100% coverage) and output schema, the description adequately covers core purpose, alternatives, and safety. However, the vague 'fine intervals' reference may confuse users since the schema includes 1m/5m/15m, and it does not explain what 'trend-index' specifically means (e.g., whether it's an aggregated index or per-symbol). Still, the output schema covers return structure.

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

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

Schema description coverage is 100%, so the baseline is 3. The description's 'optional indicator bundle' loosely maps to with_indicators but adds no additional parameter semantics beyond what the schema already states (e.g., 'include technical columns'). No new detail on size, period, start_time, etc.

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 the tool provides 'Trend-index OHLCV for symbols, with optional indicator bundle,' which clearly identifies the resource and scope. However, it lacks an explicit verb like 'get' or 'retrieve,' and the distinction between 'fine intervals' in the alternative and the schema's 1m/5m timeframes creates slight ambiguity about what this tool actually covers.

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 alternatives: exchange pair/contract candles or fine intervals → marketdetail_get_kline, columns → get_indicator_history, chart-label snapshot → get_technical_analysis. This provides clear when-not-to-use guidance and distinguishes the tool from its siblings.

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

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

While annotations already declare readOnlyHint=true and destructiveHint=false, the description adds useful behavioral context: 'Read-only public research data', 'No account access, no order placement or fund transfers', and 'Not investment advice'. This goes beyond the annotations by clarifying non-investment nature and access scope, enhancing transparency.

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

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

The description is concise, with three sentences that each carry valuable information. It front-loads the core purpose, then distinguishes from alternatives, and finally adds safety/disclaimer context. No redundant or filler words; every part earns its place.

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

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

Given the tool's complexity (4 parameters, 1 required) and full schema coverage, the description sufficiently covers the data source (OHLCV-only), research nature, disclaimers, and alternative tools. With an output schema present, the lack of return-value explanation is acceptable. It is complete enough for an agent to select and invoke correctly.

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

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

The input schema covers all parameters with descriptions (100% coverage), so the schema itself documents the parameters. The description adds minimal parameter-specific context beyond the schema, such as implying the 'period' parameter through 'Multi-timeframe'. Since the schema does the heavy lifting, a baseline score of 3 is appropriate.

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

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

The description clearly identifies the tool's purpose: generating multi-timeframe chart-derived labels (bullish/bearish/neutral summaries) from OHLCV data. It distinguishes itself from sibling tools by explicitly noting 'OHLCV→get_kline' and 'Raw columns→get_indicator_history', making it clear what this tool does and what others do.

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 usage guidance by indicating that this tool is for descriptive research labels, not forecasts or investment advice, and contrasts it with get_kline for OHLCV and get_indicator_history for raw columns. It implicitly tells when to use this tool vs. alternatives, though not as a formal 'use when...' 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?

Annotations already declare read-only, open-world, idempotent, and non-destructive. The description adds valuable context beyond that: output structure (token_balances USD desc), Solana-specific additions, possible errors, chain aliases, and disclaimers, all consistent with annotations.

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

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

The description is dense but every sentence earns its place: main purpose, feature list, chain aliases, errors, sibling redirection, and disclaimers. Front-loaded with the wallet profile statement; no redundant content despite the high information density.

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 and annotations, the description covers the tool's feature set, chain handling, error scenarios, alternative tool, and access limitations. There are no significant gaps that would hinder an agent from selecting and invoking this 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 covers 100% of 6 parameters with descriptions, so baseline is 3. Description adds meaningful supplement by mapping chain aliases (op→optimism, avax|avalanche-c→avalanche, etc.) and noting that detailed maps to full, which helps agents pick correct values beyond the schema's generic examples.

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

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

Description opens with 'Wallet profile' and enumerates specific contents (asset_summary, token_balances, multi_chain_token_balances, labels/risk), making it clear this fetches address information. It also distinguishes itself from the sibling get_address_transactions by explicitly redirecting transfer queries, demonstrating a precise verb+resource+scope.

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

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

Explicitly names an alternative: 'Transfers→get_address_transactions'. Also states 'Read-only public research data' and 'No account access, no order placement or fund transfers', giving clear when-to-use and when-not-to-use guidance beyond simple implied 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?

Annotations already declare readOnly, idempotent, openWorld, and non-destructive. The description adds valuable behavioral details beyond annotations: BTC items include inputs/outputs/tx_status, and the partial_upstream_response edge case when list is unparseable. It also clarifies no account access or fund transfers. These add useful context without contradicting 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 relatively concise but somewhat disjointed. It mixes core functionality, an edge case, a pointer to a sibling tool, and safety disclaimers in an unstructured sequence. The disclaimer portion repeats similar ideas (no account access, no fund transfers, not investment advice). While not overly long, it could be more tightly organized.

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 100%-covered schema, output schema, and annotations, the description adds sufficient context: pagination, BTC-specific fields, an upstream edge case, and safety guards. It does not need to explain return values due to the output schema. However, it could briefly mention supported chain variations or standard filter behaviors, but overall it is complete enough for a well-documented tool.

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

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

The schema already provides 100% coverage for all 13 parameters with detailed descriptions. The tool description adds minimal parameter-specific semantics, only mentioning 'Chain aliases same as get_address_info' for the chain parameter. Baseline is 3 due to high schema coverage, and the description does not significantly 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 begins with 'Paginated transfers,' which clearly indicates the tool retrieves transaction transfers with pagination. The tool's name includes 'get_address_transactions,' making the resource explicit. It distinguishes itself from sibling info_onchain_get_address_info via 'Profile→get_address_info,' though it doesn't explicitly contrast with other transaction-related tools.

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

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

The description provides some usage context, such as 'Chain aliases same as get_address_info' for consistent chain naming and 'Profile→get_address_info' to redirect profile requests. However, it does not explicitly state when to use this tool versus alternatives like info_onchain_get_transaction or info_onchain_get_token_onchain, leaving guidance incomplete.

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=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context: 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.' This clarifies access limitations and disclaims financial advice, going 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 two sentences, front-loaded with the most important scope information. It wastes no words, and the use of arrows and short clauses makes the alternative routing highly scannable. Every phrase earns its place.

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

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

Given the 100% schema coverage, output schema presence, and strong annotations, the description does not need to repeat return behavior. It covers safety, alternatives, and scope boundaries. The absence of rate limits or auth requirements is acceptable given the 'public research data' note and openWorldHint=true. Overall complete for a read-only token lookup tool.

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

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

Schema description coverage is 100%, so the schema already documents all parameters (chain, scope, token, upstream_raw_mode, include_upstream_raw). The description adds marginal value with the scope list 'holders, transfers, activity, smart_money' which aligns with the schema's scope enum, but does not explain parameter syntax or edge cases beyond that.

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

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

The description clearly indicates a token-focused on-chain tool covering holders, transfers, activity, and smart_money. It distinguishes from sibling tools by explicitly pointing to get_address_transactions for address ledgers and get_transaction for single transactions. Though there is no explicit 'get' verb, the tool name and scope list make the purpose 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 provides explicit alternatives: 'Address ledger→get_address_transactions. One tx→get_transaction.' This tells the agent when not to use this tool and which sibling to choose. It also implies usage for token-centric queries, though it doesn't explicitly state 'use this when you need token data'.

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 and non-destructive behavior. The description adds that 'fields sparse if upstream thin', which is a non-obvious behavioral trait not available from annotations. This provides extra transparency beyond the structured safety 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 extremely concise with five short sentences, each serving a distinct purpose: core function, sparse-field caveat, sibling pointer, read-only reassurance, and disclaimer. It front-loads the key action and avoids unnecessary detail.

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

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

With an output schema present and annotations covering safety, the description only needs to add behavioral caveats and use-case context. It covers the sparse-field behavior, account/fund restrictions, and research suitability, making it sufficiently complete for this simple 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 covers 100% of parameters with clear descriptions, so the baseline is 3. The description does not add new meaning beyond identifying the core transaction hash, which is already self-explanatory. Schema does the heavy lifting.

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

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

The description 'One transaction by hash' uses a specific verb and resource, clearly identifying the tool's function. It also distinguishes from siblings by pointing to get_token_onchain for token views, which differentiates it from similar lookup tools.

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

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

The description provides explicit usage context: 'Read-only public research data' and exclusions like 'No account access, no order placement or fund transfers'. It also names an alternative tool via 'Token view→get_token_onchain', giving direct guidance on when to use a different 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?

Beyond the readOnlyHint, openWorldHint, and idempotentHint annotations, the description adds concrete behavioral details: 'No account access, no order placement or fund transfers' and 'Not investment advice'. This provides practical context about what the tool does not do, adding value over the annotations alone.

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

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

The description is three sentences: purpose, alternative usage, and safety disclaimer. Each sentence carries distinct information, though the second sentence's arrow syntax is slightly cryptic. Overall, it is compact and front-loaded.

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

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

With a rich output schema and clear annotations, the description covers the essential context: what the tool returns (ranking/breakdown), safety guarantees, and a pointer to a related tool. It does not elaborate on output structure, but the output schema fills that gap, making the description adequate.

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

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

The input schema has 100% description coverage for all four parameters, so the description does not need to repeat parameter details. It adds no extra semantics about how parameters interrelate, so the baseline score of 3 is appropriate.

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

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

The description states the tool provides 'Bridge ranking or one-bridge chain breakdown', which is a specific resource (bridge metrics) and implies a list/detail action. It differentiates from siblings by referencing get_defi_overview for broader cross-sector dashboards, though the phrasing is somewhat terse.

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

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

It gives an explicit alternative ('bridge→get_defi_overview') for cross-sector dashboards, implying this tool is for bridge-specific rankings or per-bridge breakdowns. However, it does not exhaustively distinguish from all sibling platform-metrics tools, leaving some ambiguity about when to prefer this over chain_activity or defi_overview.

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, destructiveHint. The description adds context about no account access, no order placement, no fund transfers, and 'not investment advice', along with the data source. It doesn't contradict 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 compact and front-loads the core purpose, but includes the cryptic 'Gate native ladder→get_orderbook' phrase and a standard disclaimer that add little value. The core content is efficient, but the extra phrase hurts 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?

With a full output schema, strong annotations, and complete parameter documentation, the description provides enough context for an agent to select and invoke the tool. The ambiguous 'Gate native ladder→get_orderbook' and lack of usage exclusions are minor gaps.

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

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

All five parameters have descriptions in the schema, giving 100% coverage. The description adds only high-level context (spot/perp, BTC/ETH) but doesn't elaborate on limit, exchange, data_scope, or market_type beyond the schema.

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

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

The description clearly identifies a specific resource: competitor CEX ±1% order-book depth for spot/perp from warehouse indices, with BTC/ETH liquidity benchmarking. This distinguishes it from the raw orderbook sibling (info_marketdetail_get_orderbook) and other platform 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 suggests use for liquidity benchmarking on BTC/ETH and emphasizes its read-only, non-transactional nature. However, it does not explicitly state when to use this tool over alternatives like info_marketdetail_get_orderbook, or provide exclusion 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 well beyond the annotations. It discloses specific data limitations (e.g., 'no tx_count/l1_fee_usd' for l2, 'granularity day only'), data source tables, whitelist constraints, and explicitly states 'Read-only public research data. No account access, no order placement or fund transfers.' This provides rich behavioral context that annotations do not cover, and it does not contradict the readOnlyHint/idempotentHint 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 lengthy but every sentence carries specific information. It is front-loaded with the core purpose, then structured by metric_group, making it easy to scan. No filler or redundancy; all content is relevant to selection and invocation.

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 parameters, complex metric_group variants, and an output schema, the description provides comprehensive context: data sources, field lists, constraints, and safety disclaimers. It covers all edge cases like l2 granularity restrictions and btc_l2 whitelist behavior. The presence of an output schema means return value details are not required, and the description fully compensates for the schema's lack of descriptive depth.

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

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

Schema coverage is 100%, so baseline is 3. The description adds substantial meaning beyond the schema by listing the exact fields returned for each metric_group (e.g., tps_avg_1d, active_addresses_1d, blob_cost_usd_1d for l2; tvl_usd, protocol_count for btc_l2). It also clarifies the whitelist for btc_l2 projects, which is not in the parameter descriptions. This goes beyond what the schema alone provides.

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

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

The description clearly states the tool's purpose: 'Chain-level activity metrics by metric_group.' It then enumerates three specific metric groups (staking, l2, btc_l2) with their data sources and fields, making it distinct from sibling platformmetrics tools that cover bridges, CEX orderbooks, etc. The verb+resource (get chain activity) is specific and unambiguous.

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

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

The description provides implied usage context by explaining what each metric_group returns, but it does not explicitly state when to use this tool over alternatives or mention exclusions. There is no explicit reference to sibling tools or 'when not to use' guidance. The granularity and whitelist constraints are there, but they are more about parameter behavior than use-case selection.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds context beyond these annotations by specifying 'No account access, no order placement or fund transfers' and 'Not investment advice,' which informs the agent of limitations and risk expectations. It does not repeat the annotations verbatim, adding genuine behavioral value.

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

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

The description is compact and front-loaded: the first sentence states purpose, the next two give routing to alternatives, and the final three cover safety and limitations. Every sentence earns its place with 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 tool's low complexity (one parameter, no required params, output schema present), the description is fully complete: it explains the purpose, differentiates from siblings, provides usage alternatives, and discloses behavioral constraints. No essential information is missing for an agent to decide when and how to use 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 input schema fully describes the single 'category' parameter, including allowed values (all|defi|spot|perp|stablecoin|bridge), pass-through behavior for unknown values, and empty behavior if no match. The description adds no novel parameter information beyond what the schema already provides, so the baseline score of 3 applies due to 100% schema coverage.

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

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

The description clearly states the tool's function as a 'Cross-sector dashboard' for DeFi, spot, perp, stablecoin, or bridge categories. It explicitly differentiates from sibling tools by directing users to get_bridge_metrics for bridge ranking/chain detail and to get_platform_info for single protocol, providing a specific resource and scope.

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

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

The description gives explicit when-to-use guidance: for a cross-sector overview, use this tool; for single bridge ranking or chain detail, use get_bridge_metrics; for a single protocol, use get_platform_info. It also sets expectations that this is read-only public research data with no account access or order placement, clarifying appropriate 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 declare readOnlyHint=true, but the description adds important behavioral details: 'Read-only public research data. No account access, no order placement or fund transfers.' It also explains specific outputs for different parameter combinations, such as 'scope=full + include_flows=true returns flows.series[]', going 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 concise and well-structured, using a semicolon-separated list for scope combinations. It front-loads the primary purpose and keeps each sentence informative without clutter. Every sentence adds value, and the length is appropriate for the tool's complexity.

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

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

Given the tool's 11 parameters and conditional behaviors, the description covers the key scenarios (flows, events, PoR) and directs users to get_platform_history for TVL history. The output schema presumably handles return structure details, so the description sufficiently contextualizes when and how to use 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 covers 100% of parameters, but the description adds significant semantic value by explaining parameter interactions. For example, it clarifies that include_flows and include_events only work when scope=full, and describes their effect on the response. This conditional logic is not evident from the schema alone.

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

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

The description clearly states the tool returns 'Exchange reserve snapshots by venue and asset', which is specific and distinguishes it from siblings. It also explicitly redirects TVL history queries to get_platform_history, reinforcing its specific purpose.

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

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

The description provides clear usage guidance: it explains the conditions for using scope=full to add PoR attestation, and how include_flows and include_events modify the response. It also names an alternative tool for TVL history, giving explicit when-to-use vs when-to-use-other 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 readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds context about authentication (public, no account access), operational limits (no orders/funds), and an advisory disclaimer, which goes beyond the structured annotations.

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

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

Three concise sentences with the core function front-loaded. Safety disclaimers are useful and not verbose. Every sentence adds 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?

Tool is simple (3 params, 1 required) with an output schema. Description covers purpose, data nature, and safety boundaries. Minor gap: no mention of data freshness or symbol coverage limits, but output schema compensates.

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 parameters are already well-documented. Description only indirectly references symbol and range via 'by symbol and price buckets,' adding no new semantic detail 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 clearly states 'Liquidation density by symbol and price buckets,' which is a specific verb+resource combination. This distinguishes it from sibling tools that cover other platform metrics like bridges, reserves, or DeFi overviews.

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

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

Provides clear context: read-only public research data, no account access, no order placement or fund transfers, not investment advice. This tells the agent when safe to use but does not explicitly name alternative tools or when-not-to-use scenarios.

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=true and idempotentHint=true. The description adds valuable context beyond annotations: 'Read-only public research data. No account access, no order placement or fund transfers.' This clarifies the operational scope and limitations, exceeding what annotations alone provide.

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

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

Four sentences, all information-dense and non-redundant. The description front-loads the core purpose and then efficiently covers alternatives, parameter guidance, safety, and disclaimers. No wasted words.

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

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

Given the rich output schema, comprehensive annotations, and detailed parameter descriptions, the tool description is complete. It covers purpose, usage boundaries, alternative tools, parameter interactions, data nature, and disclaimers. No significant contextual gaps remain.

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 each parameter is already described. The description adds extra semantic value by explaining the exchange_slug/platform_name relationship for CEX perps ('pass exchange_slug (e.g. gate) or platform_name') and giving a concrete example, going beyond the schema's basic definitions.

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

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

The description opens with a specific action and resource: 'Daily TVL, volume, and fees time series for one named protocol.' It clearly distinguishes from sibling tools by naming alternatives (get_platform_info, search_platforms) and explicitly scoping to one named protocol.

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

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

Provides explicit when-to-use guidance: 'One-shot profile→get_platform_info. Ranked multi-protocol list→search_platforms.' Also gives usage direction for CEX perps history (pass exchange_slug or platform_name), clearly separating this tool from its siblings.

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

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

Annotations already provide readOnlyHint=true and destructiveHint=false, and the description reinforces this by stating 'Read-only public research data. No account access, no order placement or fund transfers.' It adds context about what the tool does not do and includes an 'not investment advice' disclaimer. There is no contradiction, and the extra context surpasses the 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, front-loaded with the core purpose, and each sentence contributes either parameter details, alternative tool references, or safety disclaimers. It is slightly dense but remains readable and efficient.

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

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

The description effectively covers purpose, usage guidance, parameter interactions, and safety behavior. Since no output schema is present, the description does not need to detail return values. The combination of annotations, schema, and description provides sufficient context for an agent to use this 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%, so baseline is 3. The description enhances this by elaborating on scope=full: 'adds competition_metrics{} for CEX venues' and clarifying the conditional interaction between include_oi_symbol_detail and oi_symbol_limit with defaults and range. This adds meaningful guidance beyond the schema's property 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 'One-shot protocol profile by name and scope,' which clearly identifies the tool's function: fetching a single protocol's profile. It also distinguishes itself from siblings by explicitly pointing to search_platforms for ranked lists and get_platform_history for daily time series, leaving no ambiguity about scope.

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

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

The description directly states when to use alternatives: 'Ranked multi-protocol list→search_platforms. Daily time series→get_platform_history.' It also implies usage for a single protocol lookup and clarifies scope options, giving the agent explicit decision 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?

Annotations already declare read-only and non-destructive, but the description adds context: 'Read-only public research data. No account access, no order placement or fund transfers. Not investment advice.' These disclosures are useful for an AI agent to set expectations. However, details like rate limits or error behaviors are absent, but the annotation coverage lowers the bar.

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 succinct and front-loaded. It opens with the core function, then enumerates sections, alternates, and caveats in a compact, scannable format. Each sentence earns its place without fluff.

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

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

Given the presence of an output schema and thorough annotation, the description covers all critical aspects: purpose, key modes, sibling distinctions, and behavioral limitations. It does not need to explain return values because the output schema exists. The pointer to alternatives rounds out the 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 input schema has 100% coverage with descriptions for all 9 parameters, so the baseline is 3. The description adds value by explaining what each section returns ('issuance_flow returns issuance_flows[]... usage_structure returns real usage metrics... depeg_events returns depeg events'), which is not in the schema. It also implies the symbol parameter's role in 'per-symbol chain breakdown.'

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: 'Stablecoin-only ranking or per-symbol chain breakdown.' It details specific sections (issuance_flow, usage_structure, depeg_events) and explicitly contrasts with sibling tools ('Broad market dashboard→get_market_overview. Cross-sector rollup→get_defi_overview.'), making the tool's niche unambiguous.

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

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

The description provides explicit when-to-use guidance and alternatives: 'Broad market dashboard→get_market_overview. Cross-sector rollup→get_defi_overview.' It also instructs that sections require scope=full, helping the agent decide parameter usage. This goes beyond mere purpose.

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 assert readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds context beyond annotations by stating "No account access, no order placement or fund transfers, Not investment advice." This clarifies the non-financial-advisory nature and absence of side effects, adding value without contradicting 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 three sentences long, front-loaded with the core purpose, and every sentence earns its place: purpose, scope details, sibling alternatives, and safety disclaimers. No redundant filler or repetition of schema 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 tool has 8 parameters, an output schema, and clear annotations, the description provides sufficient context: what data is returned, how to filter by scope, when to use other tools, and safety limitations. The output schema handles return-value documentation, so the description need not explain that. Completeness is high for an info-retrieval tool.

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

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

Schema description coverage is 100%, so parameters are well-documented. The description adds marginal value by explaining scope=full fields and the overall "by APY or TVL" concept, which reinforces sort_by semantics. However, the schema already covers parameter details, so the description does not carry a heavy burden here.

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

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

The description opens with a specific verb-resource pair: "Lending and LP pools by APY or TVL." This clearly identifies what the tool returns and how it can be sorted. It also distinguishes itself from sibling tools by explicitly naming alternatives for related but different use cases (get_platform_info for protocol profile, get_platform_history for TVL 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 provides explicit usage guidance by stating when to use alternative tools: "One protocol profile→get_platform_info. TVL series→get_platform_history." It also gives context about the read-only public research nature, ensuring the agent knows this is a safe, non-transactional query. This goes beyond implied 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?

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds meaningful context beyond annotations: 'public research data,' 'No account access, no order placement or fund transfers,' and 'Not investment advice.' This clarifies the tool's scope and limitations without contradicting 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 exceptionally concise: three sentences covering purpose, usage alternatives, and behavioral caveats. It is front-loaded with the core function and every sentence adds unique value with no redundancy or filler.

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

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

With five optional parameters and an output schema, the description needn't detail return values. It sufficiently orients the agent: what it does (list), when to use alternatives, and the read-only public nature. This is enough for correct selection and invocation.

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

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

Schema coverage is 100%, and all five parameters (chain, limit, sort_by, sort_order, platform_type) have detailed inline descriptions. The description only mentions 'filter and sort' generically, which aligns with the schema but adds no new information. Baseline 3 is appropriate since the schema carries the full burden.

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

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

The description clearly states the tool returns a 'ranked multi-protocol list with filter and sort,' identifying the resource (platforms) and operation (ranking with filtering/sorting). It distinguishes from siblings by explicitly referencing get_platform_info for one-shot profiles and get_platform_history for daily series, positioning this as the list/search tool.

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

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

The description gives explicit usage guidance: 'One-shot profile→get_platform_info. One named protocol daily series→get_platform_history.' This tells the agent when to use alternatives, implicitly clarifying when to use this tool. It also notes 'Read-only public research data' and 'No account access' to set context for appropriate use.

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