365rwa RWA structured data (Chinese-language RWA intelligence)

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

With no annotations provided, the description carries the behavioral burden and usefully discloses that the tool is free and acts as a pre-query discovery step. It does not discuss freshness, auth, or side-effect profile, but for a zero-parameter listing tool with an output schema, the key behavioral context is mostly covered.

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

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

Two compact sentences, with the core purpose front-loaded and the usage timing immediately after. There is no redundant or filler text.

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 empty input schema and output schema cover invocation and return shape, so the description only needs to explain purpose and timing, which it does. Minor details such as data freshness or the exact format of prices are omitted but not essential for calling the tool.

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

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

The tool takes zero parameters, so there are no parameter semantics to explain. The baseline for a zero-parameter tool is 4.

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

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

The description uses a specific verb-resource pair: list all queryable RWA datasets. It also names the contents returned (record counts, corresponding tools, per-query price), making the tool clearly distinguishable from the query_* siblings as a discovery step.

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

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

It explicitly says to call this before paid queries to understand available data, which gives clear usage context. It does not name specific sibling query tools or state when not to use it, so it falls short of full when/when-not guidance.

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

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

No annotations are provided, so the description carries the full burden, and it does disclose two useful behavioral facts: the call has no cost and it exposes a payment address, which matters for an agent in a paid marketplace. It says nothing about whether the call has side effects, whether it requires authentication, or about rate limits or latency, which leaves gaps for a tool with zero annotation coverage.

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

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

Two short sentences, front-loaded with the operation and its cost profile. The second half enumerates return fields that the output schema already covers, which is mild redundancy rather than waste, since it still helps an agent pick the tool.

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

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

The output schema exists, so return values do not need spelling out, and the description still adds the two things the schema cannot: that the call is free and that it surfaces a payment address. What is missing is guidance on when in a workflow to call it, which for a health-check tool would be genuinely useful.

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

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

The tool takes zero parameters, so there is no parameter semantics to explain and the baseline of 4 applies. The description correctly does not invent parameter discussion.

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

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

The description identifies a specific operation ("健康检查") and enumerates what it returns (service status, payment address, network, price list). It is unmistakably different from every sibling (gpu_history, gpu_price, list_gpu_models, market_movers, platform_reliability), though it never explicitly contrasts itself with any of them.

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?

Saying the call is "免费" (free) implies it is a cheap pre-flight/connectivity check, and the way it is framed suggests calling it before spending money on the paid data tools. However, the description never states when to use this tool rather than a sibling, and it gives no prerequisites or exclusions.

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

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

No annotations exist, so the description carries the full burden. It usefully discloses cost ($0.02 USDC per call) and that results are bilingual, but says nothing about whether this is a pure read, result caps, or rate limits — no contradictions, just gaps.

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

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

Front-loaded with what is returned, then filters, then a runnable example, then price. Dense and mostly waste-free; the field enumeration is long but each item is informative.

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

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

With only two optional parameters and no output schema, the description covers what an agent needs: which fields come back, valid category values, a usage example, and the billing model. Only the limit semantics and read-only assurance are 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 0%, so the description must compensate. It fully compensates for category by listing the nine accepted values (treasury/credit/stock/bond/fund/commodity/newenergy/realestate/agri), which is real added meaning, but says nothing about limit beyond the example's value (e.g. default 20, maximum allowed).

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

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

States a specific verb+resource (查 RWA 发行项目档案) and enumerates exactly which record fields come back (issuer, underlying asset, size, regulator, partners, dates, official source link, bilingual). This clearly separates it from list_datasets and query_market, though it never explicitly contrasts with the nearby query_projects or verify_rwa_project.

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 category filter and a concrete example call (query_issuances(category='treasury', limit=10)) imply the intended usage, and the billing note signals it is a paid, per-call lookup. There is no explicit statement of when to prefer this over query_projects or verify_rwa_project, so routing is left to inference.

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

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

With no annotations, the description carries the full burden and does add useful traits: per-call cost of $0.02 USDC and the returned record fields. However, it does not explain limit/pagination behavior, result caps, or data freshness, leaving meaningful behavioral gaps for a paid query tool.

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

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

The description is compact and front-loaded: purpose, fields, filter, example, and pricing in a few sentences with no filler. The dense field list is slightly heavy but still 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?

No output schema and 0% parameter coverage mean the description must do more, and it partially does by naming the returned fields and pricing. It still omits limit semantics and pagination, so an agent cannot fully predict result-size behavior.

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

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

Schema description coverage is 0%, so the description must compensate. It does supply the region enum values (hk/na/eu/apac/me) and an example, which the schema lacks, but it says nothing about the limit parameter or the meaning of region's empty default.

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

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

The description states a specific verb and resource (query global licensed-institution directory) and enumerates the fields returned (institution name, license type, issuing authority, region, official register link). It does not differentiate itself from the sibling query_regulatory, which likely overlaps, so it stops short of a 5.

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

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

Usage is only implied by the region filter and a single example (region='hk' returns 15 Hong Kong licensed institutions). There is no statement of when to prefer this over query_regulatory or query_issuances, and no exclusions or prerequisites.

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

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

With no annotations, the description carries the full load; it does disclose a concrete behavioral trait, per-call billing of $0.02 USDC, which an agent needs before invoking. However it does not state that the call is read-only, whether results are paginated, or how many rows a limit can request, so the mutation/safety and result-shape profile remains undocumented.

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

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

A single dense paragraph: resource and returned fields are front-loaded, filter modes follow, then runnable examples and the price note. Every clause contributes; slight density from the slash-separated field list but no filler.

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

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

With no output schema and no annotations, the description usefully enumerates the return fields and gives usage examples plus cost, which is close to what an agent needs for a 3-param read tool. The remaining gaps are pagination/result-count behavior and the semantics of limit's bound.

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

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

Schema coverage is 0%, so the description must compensate: it explains q as a code/name keyword match and category as a category filter, which covers two of three params. The limit parameter appears only inside an example (limit=10) with no default, maximum, or behavior described, and the risk-flag enum (verified|listed|unverified) is a returned field rather than a filter, leaving its relation to the params ambiguous.

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

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

States a specific verb and resource ('查全市场 RWA 代币行情') and enumerates the fields surfaced (code/name, market cap or TVL, 24h change, spot exchange, risk flag, category). That is enough to distinguish it from data-domain siblings such as query_projects and query_regulatory, though it never explicitly contrasts itself with them.

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

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

Usage is implied through two concrete examples (query_market(q='ONDO') and query_market(category='treasury', limit=10)), which shows the two filter modes. There is no statement of when to prefer this over a sibling tool or when not to call it, so guidance stays at the implied level.

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

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

With no annotations, the description carries the full burden, and it does disclose two useful behavioral facts: the data is human-verified ('人工核查') and the tool is pay-per-call at $0.03 USDC. However, it says nothing about pagination, default result count, or failure behavior, leaving real gaps for a paid query tool.

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

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

Content is front-loaded into one dense sentence covering purpose and fields, followed by the filter capability, an example call, and pricing. No filler, though the run-on field list is dense to parse.

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

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

With no output schema, the description correctly enumerates the returned fields so the agent knows the return shape. Combined with the cost disclosure and example, it covers most of what is needed, missing only pagination/limit semantics.

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

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

Schema description coverage is 0%, so the description must compensate. It clarifies asset_class (filter by asset category) and demonstrates both params via the example, but never explains what limit does or its default of 20, and gives no hint of valid asset_class values, leaving the filtering contract underspecified.

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

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

States a specific verb+resource (查 RWA 项目评分榜) and enumerates the returned fields (评分/TVL/年化收益/链/合约地址/发行方/托管/审计/风险点), so an agent knows exactly what data it gets. It is distinguishable from sibling verify_rwa_project, though the difference from query_market is only implied.

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

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

There is no explicit when-to-use or when-not guidance, and sibling tools like verify_rwa_project and query_market are never mentioned as alternatives. The only implicit signal is the example invocation and the note that results can be filtered by asset class.

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

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

No annotations, so the description carries the burden. It usefully discloses per-call pricing ($0.02 USDC) and that results are bilingual with source links, but says nothing about pagination behavior, ordering, result size caps, or what an empty result means.

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

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

Compact, front-loaded with the resource and its payload, followed by filtering, example, and pricing. Every sentence carries information; only minor loss is the run-on field list.

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

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

For a 2-parameter read tool with no output schema, the description sufficiently covers what comes back (field list, languages, source links), how to filter, and the cost. Auth/prerequisite information is the main omission.

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

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

Schema coverage is 0%, so the description must compensate, and it does: it enumerates the valid region values (hk/cn/na/eu/apac/me/global) that the schema entirely omits, plus a worked example showing limit usage. It does not explain limit semantics (default/max), keeping it from a 5.

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

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

States a specific verb+resource (query global regulatory approvals tracking) and enumerates the returned fields: regulator, type, approved entity, title, abstract, date, official source link, bilingual. This is clearly distinct from siblings like query_licenses and query_issuances, though it never names them explicitly.

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

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

Provides an example call with region and limit, and implies filtered retrieval, but gives no guidance on when to prefer this over query_licenses or query_issuances. Usage is only implied by the region filter.

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

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

With no annotations, the description carries the full disclosure burden and mostly meets it: it spells out the five verdict levels and their meanings, says the response includes per-database hit counts, evidence samples and official source links, and discloses per-call cost ($0.05 USDC). It does not state latency, rate limits, or how ambiguous/partial matches are treated.

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

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

Front-loaded with purpose, then mechanism, then verdict scale, then example, then price — a logical order with little waste. The five-level enumeration is dense but each level earns its place, since it defines the output.

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?

No output schema and no annotations, so the description must cover return semantics — and it does, defining verdict levels, hit counts, evidence samples, and source links. Pricing is disclosed. Remaining gaps are edge-case behavior (partial matches, unknown inputs, error modes) rather than anything that blocks correct invocation.

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

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

Schema coverage is 0% — the single required parameter 'name' has no description in the schema. The text gives one example value ('BUIDL') and implies it can be a project, token, or institution name, but does not say whether tickers, full legal names, or contract addresses are accepted. This is a modest value-add over the bare schema field.

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

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

States a specific verb (核查真伪 = verify authenticity) plus a precise resource scope (RWA 项目/代币/机构) and explains the mechanism: a single call cross-checking five named databases, returning a five-tier verdict. This clearly distinguishes it from the sibling query_* tools, which each hit only one database.

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

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

The description implies usage via '一次比对五个数据库' (compare five databases in one call), which tells the agent this aggregates what query_projects/query_licenses/query_market/query_regulatory would otherwise need several calls to cover. A worked example (verify_rwa_project(name='BUIDL')) anchors the expected usage. It lacks explicit when-not-to-use guidance, such as when to prefer the individual query tools.

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