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

With no annotations, the description carries the behavioral disclosure burden. It does disclose local computation, no network access, and output written to file_path as CSV. However, it does not disclose whether an existing output file is overwritten or whether input files are strictly read-only.

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

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

The description is a single dense sentence that front-loads the core purpose, then efficiently enumerates options and side effects. Every clause adds useful information, with no filler or repetition of the schema.

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

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

For a 7-parameter tool with no annotations and no output schema, the combination of description and schema covers the input constraints, alignment modes, fill behavior, resampling, defaults, and output path. The main residual gap is overwrite behavior, which is minor.

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 reinforces defaults like close, union/intersection, forward-fill, and weekly/monthly resampling, but these are essentially also carried by the input schema. It adds little beyond what the schema already provides.

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

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

The description states the exact operation: aligning multiple library-produced CSVs by date into one wide table, with a default value column of close. This clearly differentiates it from the query_* sibling tools and from the raw name alone.

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 specifies when to use it: on CSV files produced by this library, with pure local computation and no network access. It does not name alternatives explicitly or list exclusion rules, but the scope is clear enough to route an agent correctly.

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

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

There are no annotations, so the description carries the burden of disclosure. It does disclose a key side effect: results are written to a CSV file at the given file path. However, it does not mention overwriting behavior, rate limits, or any other side effects, leaving 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?

The description is exactly two sentences with no filler. The core action ('Search arXiv papers') is front-loaded, followed by the critical output behavior. Every word earns its place.

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

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

For a tool with no annotations and no output schema, the description covers the main purpose and the output side effect. However, it omits any clarification about the tool's return value, whether the tool creates or overwrites the file, and any limits or edge cases. These are gaps for a tool that writes files, so the description is adequate but not thorough.

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 75% of parameters with descriptions, so the baseline is 3. The description adds minimal semantic value by specifying that the query targets 'arXiv papers' and that the output is CSV, but this is already partially implied by the schema and tool name. It does not significantly compensate for the undocumented sort_by parameter.

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

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

The description states a specific verb ('Search') and resource ('arXiv papers'), which clearly distinguishes it from sibling query tools focused on financial instruments. An agent can tell this targets academic literature without opening the schema.

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 implied usage: it is meant for searching arXiv papers, inferred from the tool name and first sentence. However, it provides no explicit guidance on when to use this tool versus other query tools, no exclusions, and no mention of alternatives.

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

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

No annotations, so the description carries the burden. It discloses that output is written to a CSV file and lists known limitations (missing YTM, redemption terms, etc.), which is useful. However, it doesn't disclose whether the operation is read-only, error behavior, or any side effects beyond file writing.

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 structured: main purpose, kind enumeration, limitations. It's slightly verbose but each sentence adds value, and the core purpose is front-loaded.

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

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

For a 7-param tool with no output schema, the description covers the main purpose, kinds, and known limitations. It doesn't explain return values (but CSV file output is clear) or error handling. Given schema richness, it's reasonably complete.

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

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

Schema covers 100% of parameters, but description adds mapping from kind to specific data source names (e.g., bond_china_yield), enriching meaning beyond schema. Also notes mutual exclusivity in schema, reinforcing the semantic value.

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 specific resource (China onshore bonds) and enumerates three distinct kinds, making the tool's scope clear. Doesn't explicitly differentiate from sibling query_convertible_bond but the name and scope are sufficient for a basic distinction.

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 per-kind context (what each kind returns) and known limitations, but no explicit guidance on when to use this tool vs alternatives. It implies usage by naming data sources but lacks exclusionary criteria or alternative tool references.

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 behavioral burden. The description discloses a non-obvious side effect: output is written to file_path as CSV, and it also handles the special issuer_finance case with a guidance prompt for municipal and non-listed issuers. It does not mention overwrite behavior or error cases, but the core behavioral traits are covered well.

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 and file output. Each kind clause earns its place. Some encoded Chinese text could be clearer for non-Chinese readers, but there is no redundance.

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 10-parameter, 4-mode tool with no output schema, the description covers what each mode returns, the CSV destination, and an edge-case behavior. It does not spell out all combinations, but it provides enough context for an agent to configure required and mode-specific parameters 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 already have descriptions. The tool description still adds real value by mapping each kind to its expected content and data source, and by associating history mode with periods and symbols. This goes beyond the schema's terse field descriptions.

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

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

The description clearly states 'Query China convertible bonds' and defines four distinct kinds (overview, terms, history, issuer_finance) with data sources and content. This is specific enough to distinguish it from siblings like query_bond and query_stock.

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 four kind values give implicit usage guidance, but the description does not explicitly state when to prefer this tool over query_bond or query_stock, nor does it give exclusion conditions. It provides clear context for this tool itself but lacks explicit alternative routing.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals data sources (Sina, Tencent), price adjustment (no adjustment, raw prices), date coverage (daily from ~2012, min ~8 trading days), and explicit error handling for minute over-coverage. This goes beyond basic operation and gives the agent clear expectations about output and limitations.

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

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

The description is compact and front-loaded with the core purpose and output format. It mixes English and Chinese but remains efficient, covering key behavioral details in two sentences. No wasted words, though the Chinese phrases could be seen as less accessible to non-Chinese readers.

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 data-query tool with a complete schema and no output schema (since output goes to file), the description covers the essential operational details: output path, data sources, coverage, and error behavior. It does not explain return values (not needed as output is written to file) and the schema already documents parameter formats. The description is sufficient for correct invocation.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value by clarifying the data source and coverage behavior tied to period and freq (e.g., min uses Tencent source with ~8 days coverage), which enriches the schema's enum descriptions. This extra context helps the agent select appropriate parameter values.

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 queries China onshore-listed ETFs and outputs CSV to a file path. It distinguishes itself from siblings like query_stock and query_index by explicitly targeting ETFs, though it does not name alternatives.

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

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

The description implies usage when ETF data is needed but provides no explicit guidance on when to prefer this over sibling tools. It does mention data source differences (Sina for daily, Tencent for min) and coverage limitations, which helps decide when to use it, but no exclusions or alternative recommendations are given.

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

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

With no annotations, the description must disclose behaviors itself. It clearly states the side effect of writing to file_path as CSV and the error policy for minute data coverage ('explicit error with guidance, no silent degradation'). It also mentions special start-date caveats for IF0, which helps agents reason about data availability.

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 reasonably compact and front-loads the purpose, but the mixed-language style and dense run-on clauses reduce readability. It could be structured as bullets for kind=hist and kind=contracts, and several bounded parentheticals make it hard to scan.

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 an 8-parameter tool with no output schema, the description covers the core behavior (query type, data coverage, file side effect, error disclosure). Remaining details of params like trade_date and freq live in the schema, which agents can consult directly, so the essential context for correct usage is mostly present.

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

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

Schema coverage is 100%, but the description adds substantial meaning beyond enum labels: it explains what kind=hist output is (continuous/variety daily history), what kind=contracts returns (variety contract lists like IM/RB), and adds date constraints (IF0 only 2017-01-17 onward, minute requires start/end with ~4 trading days). This is far beyond schema descriptions.

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

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

Statement 'Query China futures' immediately identifies the verb and resource, and the description separates the two modes (kind=hist vs kind=contracts) and the CSV output, clearly distinguishing this from sibling query_stock/query_bond/query_index 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 concrete usage conditions: which kind to use, that minute-period data requires start/end dates, and that coverage errors are surfaced loudly rather than silently degraded. It doesn't explicitly compare to sibling tools, but the rules for choosing hist vs contracts and data coverage are sufficiently explicit.

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

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

With no annotations provided, the description carries full responsibility. It discloses the output method ('written to file_path as CSV'), mentions default behavior for currency, and notes error behavior for cross ('不可达时明确报错'). It does not mention potential side effects like overwriting files, but it is reasonably transparent for a query tool.

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

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

The description is long but well-structured, using a kind-by-kind breakdown that makes the information digestible. It avoids redundant phrasing and each sentence adds value (examples, notes, constraints). It could be slightly more compact, but the current length is justified by the complexity of the tool.

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

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

Given the tool's complexity (multiple kinds with distinct parameter requirements) and the absence of an output schema, the description covers all necessary operational details: parameter constraints, defaults, examples, and error behavior. It does not mention broader context like rate limits or authentication, but that is not essential for correct invocation.

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

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

Schema coverage is 100% for parameters, so the baseline is 3. The description adds significant extra value by explaining each kind in relation to parameters (e.g., 'currency 过滤币种', 'start_date/end_date required for bochina'), providing examples, and clarifying defaults. This exceeds the schema's basic 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 states a specific verb ('Query') and resource ('FX rates'), and clearly differentiates from sibling tools by explicitly enumerating the kinds of FX data (mid, bochina, usdcnh, cross). This leaves no ambiguity about the tool's purpose.

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

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

The description provides detailed guidance on when to use each kind (e.g., 'kind=bochina' for Chinese bank rates, 'kind=cross' for cross pairs) and includes practical notes like '港币 not 港元' and '默认 all 25'. It does not explicitly contrast with sibling tools, but the purpose is clear enough that an agent can infer when to invoke this tool.

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

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

With no annotations provided, the description carries the full burden. It discloses output to CSV, data sources (New York Fed, CBOE, etc.), fallback behavior (东财失败自动回退 Yahoo), and constraints (短端期限仅近 1000 交易日), providing rich behavioral 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 compact but dense, with each kind explained in a structured manner. It is slightly verbose due to the level of detail, but every sentence carries useful information, so it remains 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 covers all kinds, data sources, fallback logic, date ranges, and tenure constraints. It also mentions the output format (CSV). For a tool with this complexity, the description is complete and leaves no critical gaps for an agent to configure calls 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 description adds significant meaning beyond the schema. It explains each kind's data content, start dates, tenure options, and specific constraints (e.g., short-end tenures limited to ~1000 trading days). This goes well beyond the schema's basic field descriptions.

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

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

The description clearly states the tool's purpose: 'Query global rates for backtesting.' It specifies the resource (global rates) and the action (query), and the breakdown by kind (us_treasury, fed_rate, dxy, vix) distinguishes it from sibling tools like query_bond or query_fx.

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

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

The description implies usage for backtesting and details data sources and constraints, but it does not explicitly contrast with alternative tools or state when not to use this tool. The guidance is implied rather than explicit.

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

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

With no annotations provided, the description carries the full disclosure burden — and it excels. It reveals output format/location (CSV to file_path), data source routing by symbol prefix, latency behavior (~10s for CSI), coverage limits (min only ~8 trading days for Shenzhen/Shanghai via Tencent), and error behavior (clear error + supplement guidance when minute coverage is exceeded). This is exemplary disclosure of behavioral traits.

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

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

Three dense sentences with the purpose and output format front-loaded before the data-source caveats. No wasted words — every clause (latency, coverage, error behavior) earns its place. It could arguably benefit from paragraph separation for scannability, but for a single-block description it is efficiently packed.

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 6-parameter tool with no output schema, the description is thorough: it covers purpose, output destination/format, data source selection rules, latency, coverage limits, and failure behavior. Since output is written to a CSV file at file_path, a return-value description is unnecessary. The main gap is the absence of explicit sibling differentiation, which is a usage-guidelines concern rather than a completeness one.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds genuine value beyond the schema: it explains that symbol prefix determines the data source (000xxx/399xxx vs 930xxx/950xxx) and that period=min is restricted to Shanghai/Shenzhen indices — semantics not present in the parameter descriptions. This elevates it above 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?

States a specific verb+resource ('Query China indices') that clearly identifies the tool's domain. The resource type (indices) distinguishes it from most siblings (bonds, stocks, futures, ETFs, options, FX), though it does not explicitly name the closest alternative (query_stock) which could also fetch index-like data.

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 valuable usage context: data source routing by symbol prefix (000xxx/399xxx via Sina, 930xxx/950xxx via official site), the ~10s latency caveat for CSI series, and the period=min constraint (~8 trading days coverage, clear error + supplement guidance). However, it never explicitly names sibling alternatives or states when to prefer this tool over query_stock/query_yfinance — usage guidance is implied via data-source constraints rather than explicit tool selection rules.

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

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

With no annotations provided, the description carries the full responsibility for revealing behavior. It clearly states that output is written to a file_path as CSV, and the use of 'Query' implies a read-only operation. However, it does not mention whether the file is overwritten, whether any network requests are made, or any potential side effects beyond file creation.

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

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

The description is compact and information-dense, with no fluff. It uses a structured format with bullet-like separations for the kind values, and the key operational note about finding contract codes is succinctly embedded. Every sentence contributes to understanding the tool, and the mixed Chinese/English is efficient for the intended domain.

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

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

The description provides enough context for an agent to use the tool correctly: it covers the data scope, output format, the three query kinds, and a workflow tip. Since there is no output schema, it does not need to describe return values. However, it could be more complete by explicitly stating that the 'hist' kind requires start_date and end_date, or by noting default behaviors, but overall it is sufficient for basic usage.

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

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

The schema descriptions cover all parameters, and the tool description adds meaningful context: it explains that 'kind' controls the query mode, that 'underlying' applies to months/contracts, that 'trade_date' is for contracts/CFFEX, and that start_date/end_date are for hist. This goes beyond the schema by clarifying which parameters are relevant for each kind, making the semantics clearer.

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 queries China options, specifically SSE ETF options and CFFEX index options (IO/HO/MO), which distinguishes it from sibling tools like query_etf, query_index, and query_futures. It also indicates the output is written to a CSV file, giving a complete picture of the tool's primary 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 explains the three 'kind' values (months, contracts, hist) and provides a practical hint: '本轮仅日线' (only daily data for now) and '找合约代码先用 months/contracts' (find contract codes via months/contracts first). This guidance helps the agent choose the correct workflow, though it does not explicitly compare to alternative sibling tools.

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

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

The description discloses that output is written to a CSV file at file_path, and notes that sy daily fetching is slow. However, without annotations, it does not mention any other side effects or potential errors, leaving some behavioral transparency gap.

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

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

The description is a single run-on sentence mixing English and Chinese, making it less clear. It could be organized into separate points for each kind, but currently it is somewhat cluttered.

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

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

The description provides enough context to use the tool: it explains the two kinds, required parameters, output format, and performance caveats. It even gives examples of valid symbols, which helps an agent construct correct queries.

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 has detailed descriptions for each parameter, including required conditions for each kind. The main description adds context about the two query modes and the 10-year depth for sge, but this information is mostly redundant with the schema.

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

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

The description clearly states 'Query spot prices' and details two kinds (sge and sy) with specific examples. It distinguishes the tool as a spot-price query, which helps an agent identify its purpose among sibling tools, though it does not explicitly name alternatives.

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 specifying which parameters are required for each kind: symbol for sge, symbols and dates for sy. It also notes that sy fetching is slow and limited to 1-year ranges, which informs decision-making.

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

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

With no annotations provided, the description carries the full burden. It explicitly mentions the side effect of writing output to a CSV file via file_path, which is a key behavioral trait. However, it does not disclose other behaviors like read-only nature, error handling, or rate limits, making the transparency partial but acceptable.

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, consisting of only two sentences. It conveys the core purpose and output destination with no unnecessary words, perfectly matching the desired brevity and structure.

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, combined with the detailed parameter schema, gives the agent everything needed to call the tool correctly. It specifies the output format (CSV) and the target file path. It does not explain return codes or errors, but for a data query tool this is not critical. Overall, it is complete for the intended use.

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

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

The input schema already provides descriptions for all 8 parameters with 100% coverage. The description text adds no additional meaning beyond the schema, such as reasoning for the default adjustment type or the relationship between period and freq. This meets the baseline but does not exceed it.

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

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

The description clearly states the action (Query), the resource (historical stock prices), and the scope (A-share, Hong Kong, or US markets). This sufficiently distinguishes it from sibling tools like query_bond and query_index, which target different asset classes.

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

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

The description does not explicitly state when to use this tool versus alternatives, but the tool name and description make it obvious for stock price queries. It would benefit from a note such as 'use for stocks only, not for bonds or indices' but the current wording is adequate for basic 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?

No annotations are provided, so the description carries the burden. It discloses output format (each row contains effective range/source/confidence), confidence levels, and the special behavior for commodity_futures. It does not mention side effects like overwriting the output file, or potential error cases, but for a read-only query tool this is acceptable. It also does not explicitly state it is read-only, but the nature of querying rules implies it.

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

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

The description is a single dense paragraph but packs useful information: what is queried, the as_of semantics, output columns, confidence levels, special market behavior, and file output. It is slightly long but every sentence carries substantive info, and key points are 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?

For a tool with 4 params, full schema coverage, and no output schema, the description covers the core semantics well: what it returns, how as_of works, and the special commodity_futures case. It lacks explicit mention of error behavior or whether the output file is overwritten, but these are minor. The confidence levels and market-specific behaviors are sufficiently explained.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value by clarifying the meaning of 'as_of' (matching effective interval, default today) and elaborating on the 'market' enum values (e.g., cffex = 股指期货/期权品种). It also explains the 'parameter' filter is case-insensitive substring on parameter column. This goes beyond schema descriptions.

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

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

The description clearly states the tool queries Chinese trading rules parameters (stamp tax, transfer fees, price limits, T+1, margin rates, etc.) with an effective-date matching by 'as_of'. It distinguishes itself from the many query_* siblings by specifying the domain (trading rules) and the output (CSV file). However, it does not explicitly contrast with siblings, so it's clear but not maximally distinctive.

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

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

The description explains the default behavior (default to today when as_of is not provided) and gives a specific note for market=commodity_futures (returns a guidance row for exchange settlement parameters). It does not mention when not to use this tool or alternatives, but the specialized domain and output make the usage context fairly 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?

No annotations are provided, so the description carries the burden. It discloses the output behavior ('Output is written to file_path as CSV'), which is a side effect. However, it does not mention whether the tool is read-only in other aspects, any network usage, or potential errors. Partial transparency is 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 a single, concise sentence with no redundant words. It efficiently conveys the purpose and key output detail.

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

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

Given the simplicity of the tool (5 required parameters, no output schema), the description is fairly complete. It explains that output is written to a CSV file, which is essential. However, it does not clarify the return value (e.g., success indicator) or error handling, but these are minor gaps for such a 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 descriptions cover 100% of parameters with examples for country and indicator. The tool description itself does not add additional meaning beyond the schema, so it aligns with the baseline of 3.

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

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

The description clearly states 'Query World Bank macroeconomic indicators', specifying both the verb (query) and the resource (World Bank). This distinguishes it from sibling tools that target other sources like arXiv, bonds, stocks, etc.

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

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

No explicit guidance on when to use this tool over alternatives. The name and description imply use for World Bank data, but the description does not directly contrast with siblings or provide conditions for 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?

The description discloses the default data provider (akshare) and the fallback option (yfinance), which are behavioral choices. It also implies side effects via the required 'file_path' parameter (output CSV). No annotations are provided, so the description carries the transparency burden and handles it reasonably well.

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

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

The description is concise (two sentences) and front-loads the primary purpose. It avoids redundancy and directly addresses the key differentiator (data source selection). The structure is clean and easy to parse.

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

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

The description covers the main purpose and data source behavior. It does not elaborate on output format or error handling, but given the absence of an output schema and the simplicity of the task, the provided information is largely sufficient. The description complements the schema without major gaps.

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

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

Schema coverage is high (83%), with descriptions for most parameters. The tool description adds valuable context by explaining the default behavior of 'use_yfinance' (even though the parameter description says 'Use yfinance instead of akshare', it does not state which is default). This extra detail enhances understanding beyond the schema.

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

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

The description clearly states the tool's function: 'Query historical prices for US/global tickers.' It specifies a verb ('Query') and a resource ('historical prices'), and the mention of akshare/yfinance distinguishes it from sibling query tools that target other asset classes or data sources.

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

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

The description explains the data source selection: 'Defaults to akshare (free, no key); set use_yfinance=true to fall back to Yahoo Finance.' This provides guidance on when to use the tool and how to switch between providers. It does not explicitly compare to sibling tools, but the data source context is useful.

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?

It transparently notes that output is written to a file (file_path) and describes the matching logic, including empty candidate cases. It does not mention any destructive side effects, but the file writing is a clear side effect.

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 but mixes English and Chinese, which may reduce clarity for some readers. The structure is a bit disjointed with multiple clauses, but it remains brief and does not include unnecessary fluff.

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

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

It covers the main aspects: input, output location and format, matching behavior, and a follow-up step. It does not specify error handling or edge cases beyond the non-listed issuer scenario, but for the tool's simplicity, it is fairly complete.

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

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

The description adds significant meaning beyond the schema: it explains that keyword can be an abbreviation or full name, details the exact matching rules (abbreviation exact, full name substring), and clarifies the output content. This goes well beyond the basic 'Stock name or keyword' and 'Output CSV file path' in the schema.

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

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

The description clearly states the tool's purpose: resolving an A-share stock code from a company name. It also mentions the output format (CSV) and distinguishes it from sibling tools like query_stock which fetch market data.

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

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

It provides guidance on when to use it (for resolving codes by abbreviation or full name) and even suggests a follow-up action (calling query_stock when multiple candidates exist). However, it doesn't explicitly state when not to use it or alternatives.

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