cibo

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

With no annotations, the description carries the burden of behavioral disclosure. It implies a read-only comparison and usefully specifies the cardinality and delimiter, but it does not state read-only intent explicitly or describe failure handling, invalid-code behavior, or any access constraints. This is a moderate gap for a simple query-like 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?

A single structured sentence puts the action, bound, and output fields front-loaded with no filler. The line break before the field list is slightly awkward but does not hurt parseability.

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 one-parameter tool with no annotations and no output schema, the description covers the input contract and what is compared, which is enough to form a reasonable call. It does not document the exact return shape, but the listed fields serve as an output sketch; only the ambiguity of 'change' is a real gap.

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

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

The schema only exposes a generic 'codes' string with no description, so the description's clarification that codes are comma-separated and capped at 10 is essential and adds real value. It still leaves the stock-code format unspecified (e.g., tickers vs exchange suffixes), which an agent may need to infer from sibling search tools.

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 capability — side-by-side comparison of stock metrics — and identifies the resource (up to 10 stocks) and the specific fields (prospectus, allotment, first-day close and change). This clearly separates it from single-stock siblings such as get_stock_overview or get_cmp_overview.

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

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

The phrase 'side-by-side comparison' and the explicit 10-stock cap give an agent clear context for when to choose this tool over single-stock lookups. However, it does not explicitly name alternatives or state when not to use it, leaving some overlap ambiguity with comparison-like siblings such as get_ab_comparison.

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

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

No annotations are provided, so the description must disclose behavioral traits. It only states it is a comparison matrix, implying read-only data retrieval, but does not explicitly mention side effects, data source, or any operational constraints. The agent cannot infer safety or performance implications.

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

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

The description is a single, front-loaded sentence with no wasted words. It is concise but could be more structured by adding a brief explanation of the A-tail vs B-head concept.

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 parameters and no output schema, the description is the sole source of information. It hints at the output but leaves the term 'A-tail vs B-head' unexplained, and it's unclear what exactly is being compared or what the matrix contains. This is incomplete for a no-parameter 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?

There are zero parameters, so the schema is empty. The description adds value by specifying the content of the output (oversub, expected lots, capital efficiency), giving the agent an idea of what data to expect. This goes 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 returns a comparison matrix between A-tail and B-head, listing key dimensions (oversub, expected lots, capital efficiency). The verb 'get' implies retrieval. However, 'A-tail vs B-head' is domain jargon that may not be immediately clear, and it doesn't differentiate from siblings like get_group_ab or get_oversub.

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

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

The description provides no guidance on when to use this tool versus its many siblings. It does not mention any alternatives or conditions for selection, leaving the agent to guess based on the cryptic name.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The only behavioral hint is 'pre-computed,' indicating the data is static rather than dynamically calculated. It does not explicitly state read-only behavior, data freshness, error conditions, or any side effects, leaving significant behavioral traits undisclosed.

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

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

The description is a single, front-loaded sentence with no filler or redundant details. It conveys the core idea efficiently and is appropriately sized for the tool's simple interface.

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 must explain what the tool returns. It only says 'grid,' which is ambiguous about the actual data structure, value types, and how the 18 x 5 dimensions map to oversub and alpha. It also lacks any context on when this tool is preferable to sibling prediction tools, leaving the agent to guess about result interpretation and selection.

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

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

Schema description coverage is 0%, and the description partially compensates by referencing 'stock and agent,' mapping the two parameters to their conceptual roles. However, it does not define acceptable values for 'agent,' explain the meaning of 'oversub' or 'alpha,' or describe how the parameters affect the result. This is a minimal but not complete semantic contribution.

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 resource: a pre-computed 18 oversub x 5 alpha prediction grid for a stock and agent. The tool name includes 'get' which provides the retrieval verb. It distinguishes itself from siblings like get_oversub and get_prediction through the specific grid structure and agent context. A fully explicit verb in the description would make it 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?

No guidance is given about when to use this tool versus alternatives such as get_oversub, get_prediction, or get_scatter. The description only states what the tool returns; it does not mention conditions, prerequisites, or when another sibling would be more appropriate.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly discloses the fallback behavior (ok:false for unknown/no result), the placeholder-tier behavior for pre-listing stocks, and clarifies that summary.reallocation is a raw flag, not a discretionary reallocation indicator. These are valuable behavioral nuances beyond what the schema or annotations convey.

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

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

The description is front-loaded with the main purpose, followed by structured lists of components. Each sentence adds value, particularly the caveats and the clarification of summary.reallocation. It is slightly verbose but remains focused.

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

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

For a tool with one parameter, no output schema, and no annotations, the description gives a reasonable overview of the returned data components and one field-level caveat. However, it does not describe the overall response envelope beyond ok:false, nor does it detail all field semantics, leaving some gaps for an agent trying to parse the result.

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

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

The schema has 0% description coverage, so the description must compensate for the stock_code parameter. It mentions 'a stock' and pre-listing stocks, but does not explain the expected format (e.g., numeric string, with/without leading zeros) or provide examples. This minimal elaboration adds little beyond the parameter name itself.

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

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

The description clearly states that the tool returns full allotment results page data for a stock and enumerates the components (allotment summary, international placing concentration, cornerstone allocation, Pool A/B tiers). It is specific enough to distinguish from narrower siblings like get_allotment_tiers or predict_allotment, although it does not explicitly name them. The lack of an explicit action verb (e.g., 'retrieves') is a minor gap.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives such as get_allotment_tiers or predict_allotment. It includes a caveat that pre-listing stocks return placeholder tiers, which is behavioral rather than a recommendation for selection. Consequently, an agent cannot determine how to choose among related tools without additional 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?

No annotations are provided, so the description must carry the full behavioral burden. It does disclose a key behavior: returns ok:false when no published allotment result exists. However, it does not mention any other behavioral aspects such as rate limits, authentication, or side effects. For a read-only getter, this is adequate but not comprehensive.

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 concise sentences with no wasted words. It front-loads the core purpose and data fields, then adds the error condition. 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 simple tool with one parameter and no output schema, the description covers the main purpose and a key error condition. However, it lacks usage guidance and parameter semantics, which are important for correct invocation. It is adequate but has clear 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 description coverage is 0%, so the description must explain the stock_code parameter. It only says 'for a stock', which is implicit and does not clarify the format, required syntax, or how to obtain the code. The description adds minimal value over the bare schema property.

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

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

The description clearly states it retrieves actual Pool A/B allotment tiers for a stock, listing the specific data fields (applied shares, allotted shares, hit pct, expected lots per tier). The word 'Actual' implicitly contrasts with prediction tools like predict_allotment, but it does not explicitly name a sibling or differentiate from get_allotment_result, which could be similar. This is clear but not fully distinguished.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not state conditions like 'use this when you need actual allotment data' or 'instead of predict_allotment'. The agent must infer usage from the tool name and sibling context, which is insufficient.

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

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

With no annotations, the description carries the behavioral burden. It states that the data is 'parsed from the registrar allotment dataset', which clarifies it is a derived analysis rather than raw results. It enumerates the computed dimensions, but it does not disclose data freshness, caching, or any limitations. This is adequate but not rich.

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, efficient sentence that front-loads the tool's purpose and then enumerates the output fields. The bilingual name repetition is minor waste, and the overall structure is easy 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?

There is no output schema, but the description compensates by listing the expected return content in detail. However, parameter semantics and usage context are missing, so the agent still lacks some information needed for fully confident 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 description coverage is 0%, and the description does not explain either parameter. stock_code is self-explanatory in context, but locale with its zh-CN default is not described anywhere. The description fails to compensate for the missing schema documentation.

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

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

The description clearly identifies the tool as producing an 'allottee profile' with specific demographic dimensions (total lots, person/company split, region/nationality, province, gender, age histogram/pyramid, HK ID letter/era/district). This specific resource and output set distinguishes it from siblings like get_allotment_result or get_allotment_tiers, which cover different aspects of allotment 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?

Usage is implied rather than explicit: the agent can infer to use this tool when it needs winner demographics for a stock's allotment. However, there is no direct comparison to sibling alternatives like get_registrar_analysis or get_registrar_research, and no when-to-use versus when-not-to-use guidance.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure, yet it only lists data components. The term 'merged proxy' is unexplained jargon, and the description does not state what the output looks like, whether any transformation or aggregation occurs, how the limit interacts with the multi-section return, or whether this is purely a read operation.

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 efficient sentence that front-loads the core purpose and lists the delivered sections. It loses a point because the unexplained 'merged proxy' jargon and the missing parameter semantics force an agent to seek clarification elsewhere.

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 relatively simple tool with one optional parameter and no output schema, the description does enumerate the components of the result, which is helpful. However, it leaves the 'merged proxy' term undefined and fails to clarify the limit parameter, so an agent cannot confidently call it correctly without external context.

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

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

Schema description coverage is 0% and the description does not mention the single parameter 'limit' at all. An agent cannot know what limit constrains (rows, days, entries per section) or how it interacts with the multiple breakdowns the tool returns, so the description adds zero meaning beyond the bare schema default of 60.

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-resource pair ('A-share ETF capital flow overview') and enumerates the components included (merged proxy, ETF inflow, margin balance history, sectors and ETF breakdown). This scope clearly distinguishes it from sibling tools such as get_stock_ohlc, get_cmp_overview, and get_macro_indicators, which target different data domains.

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

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

No guidance is provided on when to use this tool versus any of the 50+ sibling tools. There is no mention of exclusions, prerequisites, or alternative tools for related queries like broader market flow or individual stock flow, leaving the agent to infer applicability from the name alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only mentions 'Published blog posts' implying read-only operation, but does not disclose authentication requirements, pagination behavior, or any side effects. It does not even explicitly state it is a read operation, though that is implied. The description is minimal and lacks behavioral context.

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

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

The description is a single, clear sentence that front-loads the core purpose and lists the output fields. It is concise with zero fluff, making it easy for an agent to quickly grasp the tool's function.

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 two parameters with no descriptions, no output schema, and no annotations, the description is severely incomplete. An agent lacks essential information about how to use the parameters and what the response structure will be. While the tool is simple, the missing parameter semantics and lack of any return format details make it inadequate 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?

The schema description coverage is 0%, so the description must compensate by explaining the parameters. However, the description does not mention 'limit' or 'locale' at all. It does not explain what limit controls (pagination, count) or what locale affects (language of content). The agent has no guidance on how to set these parameters beyond their names and defaults, which is insufficient.

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 published blog posts from a specific blog (赛博畅想) and lists the included fields (title, excerpt, author, tags, date). This is a specific verb+resource and distinguishes it from the many financial data siblings.

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

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

The description implies usage for retrieving blog posts, and the tool name 'get_blog_posts' reinforces this. However, there is no explicit guidance on when to use this tool vs alternatives, nor any exclusions. Since it's the only blog-related tool among financial siblings, the usage is implicitly clear but not explicitly stated.

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 are absent, so the description carries the full behavioral burden. It does disclose pagination behavior and a market-wide scope, but it omits the ranking basis, the meaning of days, locale effects, and return format details. This is minimal useful disclosure, not comprehensive.

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 free of filler, with the pagination note earning its place. It is front-loaded and easy to scan, though the terseness contributes to semantic gaps elsewhere.

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 four parameters, no output schema, no annotations, and many similar ranking siblings, this description is under-specified. It does not explain ranking criteria, day-range semantics, locale behavior, or how this tool differs from get_stock_buyback and other ranking tools. An agent can call it, but choosing and interpreting it confidently is hard.

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 explicitly explains page and page_size as pagination controls, but days and locale receive no explanation beyond their names and defaults. Partial value is added, but not enough for full confidence.

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 phrase 'Share buyback ranking across listed companies' clearly names the resource and scope, and the market-wide framing distinguishes it from per-stock buyback tools like get_stock_buyback. However, there is no explicit verb, so the description relies on the tool name for the action.

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 when-to-use guidance is provided, and there are no explicit exclusions or alternatives. Given many sibling ranking tools, the agent is left to infer when this tool is appropriate rather than being told directly.

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

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

No annotations are provided, so the description bears full responsibility for disclosing behavior. It does not mention side effects, return format, data source, or any limitations. The description is purely declarative and offers no behavioral insight.

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

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

The description is a single sentence with no wasted words, so it is concise in form. However, it is so underspecified that the sentence adds little value; it is not front-loaded with useful context. It is concise but not effectively structured.

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

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

With no annotations, no output schema, and no parameter details, the description must stand alone. It is completely inadequate—an agent cannot determine what data this returns, how it differs from similar tools, or what 'cross-market comparison' entails. The description leaves nearly all critical context missing.

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

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

The tool has zero parameters, so the schema already fully covers parameter semantics through absence. Baseline for 0 params is 4; the description does not need to explain parameters since there are none, and it does not contradict or mislead in this regard.

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 is a vague noun phrase 'Cross-market comparison overview for peer stock context' without a clear verb or resource. It does not specify what is compared, which markets are involved, or what 'peer stock context' means. It is too ambiguous to distinguish from siblings like compare_stocks or get_scatter.

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 guidance on when to use this tool versus alternatives, no mention of prerequisites, and no exclusion of cases where a different tool should be used. The description provides zero usage 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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It only states that the output is 'rankings' and does not disclose whether the operation is read-only, what the ranking criteria are, what ordering is used, what data source/time period applies, or what a caller should expect in the response.

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 very short with no filler or repetition; every word contributes meaning. However, it is a grammatically awkward noun phrase rather than a clear sentence, and it omits even a simple verb like 'returns' or 'ranks.'

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 parameters, no annotations, and no output schema, the description is the only source of meaning, yet it is severely under-specified. It does not explain what the co-investment network is, what metric drives the ranking, whether the result is a list or single value, or how this differs from get_cornerstone_ranking.

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

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

The tool has zero parameters and an empty input schema, so the parameter dimension has a baseline of 4. The description adds useful context about the subject matter, which is sufficient given that there are no parameters to document.

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

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

The description names a concrete resource—'cornerstone investor co-investment network rankings'—and is not a tautology. It clearly implies that the tool returns a ranking, but it is a noun phrase rather than a verb statement, and it does not differentiate this from closely related siblings like get_cornerstone_ranking or get_buyback_ranking.

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

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

No guidance is provided about when to use this tool versus alternatives. The description does not mention the closest sibling tools, typical use cases, or any conditions that would select this tool over another ranking 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the tool's purpose and gives no information about the nature of the data (e.g., real-time, historical), potential performance characteristics, rate limits, or whether it is read-only. For a tool with no annotations, this is insufficient.

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, compact phrase with no redundant words. It front-loads the core purpose and avoids any fluff. It is appropriately concise for a tool with no parameters.

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

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

The description is too sparse for a tool that returns rankings. It does not explain the output format, how the ranking is determined, whether it returns a list, any filtering or sorting behavior, or what data is included. Without an output schema or additional context, an agent cannot anticipate the result 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?

With zero parameters, the baseline is 4. The description adds no parameter-specific details, but none are needed since there are no arguments to configure. The schema is empty, and the description does not contradict 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 resource: 'Cornerstone investor rankings' and the dimension 'by IPO involvement'. This is a specific, distinct tool among siblings like get_buyback_ranking or get_sponsor_ranking. However, it lacks detail on what constitutes the ranking (e.g., amount invested, number of IPOs) and does not differentiate itself from other ranking tools beyond the subject matter.

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

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

No guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites, typical use cases, or contrast with sibling ranking tools. An agent has to infer from the name and 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?

With no annotations, the description carries the full burden of behavioral disclosure. It mentions pagination and that it is a summary, but does not explain the scope of 'days', how filtering or locale affect results, or what the response structure looks like. No side effects are stated, though none are expected for a read operation.

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

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

The description is concise and front-loaded, with no filler. The two sentences each add information, though 'etc.' is vague and could be replaced with more concrete examples or scope details.

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 five parameters, no output schema, no annotations, and many sibling tools, the description is too sparse. It does not explain return values, the meaning of days, filter syntax, locale behavior, or how this tool differs from get_us_corp_actions.

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

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

Schema description coverage is 0%, so the description must compensate for the five parameters. It only hints at pagination, leaving days, filter, locale, and page_size semantics unexplained. This is a significant gap for an agent trying to invoke the tool correctly.

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 corporate actions and gives concrete examples (buybacks, dividends, placements). It is unambiguous about what the tool returns, though it does not differentiate itself from sibling get_us_corp_actions or other corporate-action-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?

There is no guidance on when to use this tool versus alternatives such as get_us_corp_actions, get_buyback_ranking, or get_stock_buyback. The description only states what it returns, not when it should be selected.

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

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It mentions pagination, which is useful, but it does not clarify whether it requires specific permissions, the scope of changes (e.g., covering only certain companies), or the meaning of the 'days' parameter (lookback window). It also leaves the return format unspecified further.

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 brief (essentially one sentence plus a single word 'Paginated.'), which is concise and front-loaded. It wastes no words, but could add minimal value without bloating, so it earns a high score for conciseness.

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

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

Given the complexity of 5 parameters, 0% schema coverage, and no output schema, the description is far from complete. It does not explain pagination behavior (e.g., page size limits), how to handle type_key, or what the response contains. An agent would have to guess or infer many details.

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

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

Schema coverage is 0%, so the description must compensate. However, it only explains pagination and mentions the 'days' parameter implicitly (from the schema) but does not elaborate on what 'days' controls or the meaning of 'type_key'. The schema itself provides defaults but no descriptions, so the agent lacks clarity on each parameter's purpose.

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

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

The description clearly states it lists director appointment/resignation/role changes, which is specific (verb 'list' + resource 'director changes'). It is likely distinct from sibling get_director_roster, which probably returns the current roster rather than changes, so it helps differentiate.

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

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

The description implicitly suggests it is for fetching a list of director changes (with pagination) but does not explicitly state when to use it versus siblings like get_director_roster or get_corporate_actions. No exclusions or alternatives are named, leaving the agent to infer 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?

With no annotations, the description carries the full burden, but it only lists output content, not behavior. It does not disclose data source, recency, locale effect, pagination, error behavior, or whether this is a read-only snapshot. 'Roster' implies static information but adds little beyond what the name already signals.

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 compact noun phrase with no wasted words and the key scoping term 'per-stock' is front-loaded. It is perhaps too terse given the lack of annotation coverage, but as a concise summary it scores well.

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

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

The tool is simple, but with no output schema, no annotations, and zero parameter docs, the description must provide more context. It leaves the agent without guidance on stock code format, locale semantics, or how this roster differs from related director tools, so it is not complete enough for reliable 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 description coverage is 0%, so the description must compensate. It clarifies that the result is per-stock, which maps to stock_code, but it never explains stock_code format or the locale parameter, which has a default of zh-CN and could affect language or content. This is insufficient for an agent to confidently fill both 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 names a specific resource ('per-stock director and executive roster') and the contained data fields (names, bio, roles), which is enough to distinguish it from siblings like get_director_changes. It lacks an explicit action verb, but the tool name 'get' plus 'roster' makes the read operation 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 phrase 'per-stock' implies this tool is for a single stock's directors and executives, and it is implicitly contrasted with broader or change-focused siblings. However, it never explicitly says when to use this over get_director_changes or other corporate-governance tools, and gives no 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?

With no annotations, the description carries the full burden of behavioral disclosure. It mentions pagination and ordering but does not state whether the operation is read-only, any side effects, or authentication requirements. The phrasing is more like a title than a description of behavior.

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

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

The description is very brief, with only two sentences, and it front-loads the core purpose. However, it is under-specified rather than concise; it omits critical details about parameters and behavior. Efficiency without completeness results in a neutral score.

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 no output schema, no annotations, and 5 parameters with zero schema coverage, the description is severely incomplete. It does not explain what 'days' means, how pagination works beyond the word 'Paginated', what the response contains, or any prerequisites. An agent would have to guess at most of the tool's 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 explain parameters. It only explains the 'event' parameter with allowed values ('buy', 'sell', or '' for both). The other four parameters (days, page, page_size, locale) are left unexplained, despite having defaults in the schema. This is insufficient for an agent to know their meaning.

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

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

The description states the tool returns disclosure-of-interest (增减持) records, newest first, which is a clear and specific resource. It distinguishes from siblings like get_stock_disclosure by its focus on增减持 events, though it doesn't explicitly name alternatives. The purpose is unambiguous.

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

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

No guidance is provided on when to use this tool versus alternatives. The only mention is the event parameter, which is more about parameter selection than tool selection. There are no prerequisites, exclusions, or alternative tool recommendations.

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 must disclose behavioral traits. It does not mention whether the tool is read-only, what happens if the stock is not dual-listed, or any error conditions. It also does not describe the output structure or how the mapping is presented.

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

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

The description is a single sentence that is concise and front-loads the purpose. It efficiently lists data sources without unnecessary elaboration.

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 (dual-listing mapping) and the absence of an output schema or annotations, the description is incomplete. It does not explain the return format, the meaning of ah_premium_at_ipo, or how the secondary markets are structured. An agent would need additional context to use 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 description coverage is 0%, and the description does not explain the 'stock_code' parameter format, such as whether it expects a numeric code with leading zeros or a ticker symbol. This leaves the agent without guidance on how to provide a valid input.

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

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

The description states a specific purpose: 'Dual-listing cross-market mapping for a stock' and specifies the data sources (ah_stock_mapping, prospectus_details.secondary_markets, ah_premium_at_ipo). It clearly distinguishes from sibling tools that focus on other aspects like prospectus or comparisons.

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 dual-listing mapping but does not explicitly state when to use this tool over alternatives like get_ab_comparison or get_prospectus. No exclusions or alternative conditions are mentioned.

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 behavioral burden, but it only discloses that results are paginated. It does not mention date-range semantics, default behavior, data freshness, or whether the calendar is historical, upcoming, or both.

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

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

The description is short, front-loaded, and free of filler. However, it is arguably too sparse given the number of undocumented parameters and the absence of annotations, so it is concise but not fully appropriately sized.

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 unannotated tool with no output schema and many similarly named siblings, the description is incomplete. It establishes the resource and pagination but lacks parameter semantics, selection guidance, and enough behavioral detail for reliable 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 description coverage is 0%, and the description adds no parameter-level meaning. The five parameters (days, page, group, locale, page_size) are entirely unexplained, so an agent cannot confidently set values without external knowledge.

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: an earnings calendar covering final/interim/quarterly results, dividends, profit warnings, and board dates. This content enumeration helps distinguish it from broad financial-data tools, though it does not explicitly name sibling 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?

No guidance is given on when to use this tool versus related siblings such as get_corporate_actions or get_financial_data. The content list implies a purpose, but there are no explicit use cases, exclusions, or alternative recommendations.

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 and no output schema, the description carries the full burden of behavioral disclosure. It only says the data is per-stock, grouped by period, and from post-listing financial data; it does not describe expected output structure, edge cases, or any operational behavior.

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

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

The description is a single sentence with no filler, and the key qualifiers per-stock and grouped by period are front-loaded. The word 'etc.' makes it slightly imprecise but acceptable for a summary.

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 no output schema and no annotations, and the description gives only a high-level summary. It omits how to format stock_code, what the period grouping actually looks like, and whether the result is a table, a list, or something else, leaving an agent without enough detail to reliably invoke it.

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

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

Schema description coverage is 0%, so the description must compensate for the single stock_code parameter. It only implies that the parameter selects a stock; it does not explain the required format, accepted identifiers, or any constraints beyond the schema property name.

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

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

The description names a clear resource: per-stock financial statements grouped by period, and gives concrete examples of the data (revenue, profit, eps). It is reasonably distinguishable from siblings by its focus on financial statements, though it never explicitly contrasts itself with get_stock_overview or get_stock_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?

There is no guidance about when to use this tool versus the many related stock-data siblings, and no exclusions or alternatives are mentioned. The context is implied at best: use it when you need financial statements.

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

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

No annotations are provided, so the description carries the full burden. It states the feed is 'machine-readable' and lists event types, but it does not disclose what the response contains, how events are ordered, whether it is paginated, rate limits, or other behavioral details. For a read-only feed, even minimal expectations like 'returns a list of events' are missing.

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 one concise sentence with a parenthetical enumeration of event types. It is not bloated, and the core subject is front-loaded. However, the phrase 'flash-event feed' is under-specified without further elaboration, and the event-type list is potentially confusing without context, so it is not a perfect 5.

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

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

With no output schema and no annotations, the description needs to provide more context to be complete. It does not explain the return format, event field details, how limit interacts with pagination, or the meaning of locale. An agent cannot determine the expected output or call semantics confidently from this description alone.

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

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

Schema description coverage is 0%, so the description must compensate for all parameters. It only explains stock_code as a filter, and does not mention limit or locale at all. The default values in the schema are unexplained, and there is no description of what 'limit' limits or how 'locale' affects output. This is incomplete 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 states the tool returns a 'flash-event feed' with a specific list of event types (ipo_launch / allotment_result / listing / inclusion / prediction) and indicates filtering by stock_code. This is a clear verb-resource pairing, though it does not explicitly contrast with sibling tools that retrieve individual event types, so it earns a 4 rather than 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?

There is no guidance on when to use this tool versus the many sibling tools such as get_allotment_result, get_prediction, or get_inclusion_batch. The description only says 'Filter by stock_code' but does not explain when an agent should prefer this aggregate feed over a specific event endpoint, nor does it mention any exclusions or alternatives.

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

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

No annotations are available, so the description carries the burden of behavioral disclosure. It only lists output elements and does not state side effects, read-only status, authentication requirements, or what kind of data is represented by 'max frozen' or 'milestones'.

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 very short and front-loaded with the core resource name and contents. It wastes no words, though its fragmentary style compresses meaning and forces the reader to infer the intended 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?

As a zero-parameter read-style tool, the absence of invocation details is acceptable, but there is no output schema and the key terms 'frozen capital', 'max frozen', and 'milestones' are undefined. The agent can likely select it for frozen-capital calendar questions but may not fully understand what the returned data means.

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

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

The tool has zero parameters and 100% schema coverage, so there are no parameter semantics for the description to clarify. With no invocation arguments required, the baseline 4 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 identifies a specific resource, a frozen capital calendar, and lists its contents (daily date series, max frozen, milestones). It is clear enough to convey the tool's domain, though it lacks a finite verb and does not explicitly differentiate it from sibling calendar-style 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?

There is no guidance on when to use this tool versus alternatives, no exclusions, and no mention of prerequisites or context. The description implies a lookup tool but leaves usage entirely 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not mention whether the operation is read-only, what the response format is, whether data is aggregated by time period, or any limits. The noun-phrase wording suggests a data retrieval tool but stops short of stating actual behavior.

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

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

The description is extremely concise and front-loaded, with no wasted words. However, it is under-specified: the short noun phrase leaves out the action and any distinguishing context, so brevity comes at the expense of usefulness.

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 should compensate by explaining what 'comparison data' means, how it is structured, and how this differs from the nearly identical get_ab_comparison. It does none of that, so an agent has insufficient information to reliably invoke the correct 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 has zero parameters and 100% schema coverage in the input schema. There is nothing for the description to add beyond what the schema already shows, so the baseline 4 applies.

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

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

The description identifies the resource ('Pool A vs Pool B aggregate comparison data') but uses no verb, so it doesn't explicitly say what the tool does with that data. It is clear enough to suggest it returns comparison data, but it doesn't distinguish this from the sibling get_ab_comparison, making it only marginally above vague.

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 guidance on when to use this tool versus siblings like get_ab_comparison or get_scatter. The description implies an aggregation/comparison use case but provides no exclusions, alternatives, or context such as 'use this for...'.

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 behavioral burden. It discloses the data categories and status examples, but does not mention response structure, pagination, sorting, or any side effects. For a read-only tool, this leaves notable behavioral gaps.

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

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

The description is two sentences, front-loaded with the tool's purpose, and includes only useful distinctions. Every clause contributes 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?

Given one optional parameter and no output schema, the description leaves the locale parameter undocumented and does not describe the return shape. An agent could call it with defaults but would lack essential context about response fields and locale 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?

The schema has one parameter (locale) with 0% description coverage, and the tool description does not mention it at all. The agent is left with no explanation of how locale affects the response or what valid values exist beyond the 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 clearly specifies the resource (homepage stock cards) and the exact content: upcoming IPOs (prelist, with status such as delayed/cancelled) and recently listed IPOs (recent). It also distinguishes this tool from more detailed alternatives by noting it returns the same data as the index page's sections.

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 context ('Same data as the index page's upcoming/recent sections') that implies a use case, but it does not explicitly state when to use this tool vs siblings or when not to use it. No alternative tools are named.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'Premium' but does not explain what that implies (e.g., authentication, rate limits, data granularity, or whether it is read-only). No side effects, requirements, or limitations are disclosed, leaving the agent with minimal 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 a single short sentence, which is concise and front-loaded with the core purpose. However, it is so brief that it omits essential context, making it under-specified rather than efficiently compact. It earns a middle score for being short but lacking substance.

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 no annotations, no output schema, and only 2 parameters, the description should provide enough context for an agent to call the tool correctly. It does not explain what 'Premium history' entails, whether it covers intraday or daily data, any restrictions on ticker format, or the meaning of limit. The description is incomplete for practical 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?

Schema description coverage is 0%, so the description must compensate for parameter meaning. It provides example ticker values (SKHY, 7709.HK) but does not explain the limit parameter's semantics or range. The defaults and types are in the schema, but no additional meaning is added for either parameter beyond the examples for ticker.

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 'Premium history for one hynix instrument' and gives concrete examples (SKHY, 7709.HK), making the verb-resource relationship explicit. It does not explicitly differentiate from siblings like get_hynix_snapshot, but the word 'history' and the examples make the purpose reasonably unambiguous.

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

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

The description gives no guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or contexts where another sibling (e.g., get_hynix_snapshot) would be more appropriate. The agent must infer usage from the name alone.

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

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

No annotations are provided, so the description must carry behavioral context. It discloses the source ('the hynix tracker service') and the returned content, and 'snapshot' implies a read-only fetch. It does not mention freshness, limits, or error behavior, but for a zero-parameter read tool these omissions are not critical.

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

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

The description is a single, front-loaded sentence that identifies the resource, purpose, and key fields with no filler or redundant phrasing.

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 no-parameter snapshot with no output schema, the description names the main returned elements and the data source, giving an agent enough context to invoke it correctly. It omits formatting and edge-case details, but the low complexity makes those non-essential.

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

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

The input schema has zero parameters, so there are no parameter semantics to clarify. The baseline for no-parameter tools is 4, and the description appropriately does not invent unnecessary parameter details.

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

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

The description clearly identifies the resource as an 'SK Hynix cross-market arbitrage snapshot' and names the contained fields (premium_pct, FX rates, base price). It is not a tautology and is specific enough to distinguish from generic stock tools, though it could more explicitly contrast with get_hynix_history.

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 word 'snapshot' and the focus on cross-market arbitrage imply this tool is for a current point-in-time view, and sibling get_hynix_history suggests a historical alternative. However, there is no explicit statement of 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?

With no annotations, the description must disclose behavioral traits itself, but it only states the action without mentioning return format, performance, side effects, or any limitations. An agent has no idea what the 'analysis' produces or how to interpret the output.

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

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

The description is a single, front-loaded sentence with no filler. It conveys the core action 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 no output schema and no annotations, the description is insufficient. It does not describe the return value, the nature of the 'analysis', or any caveats. For a batch operation that likely returns a large dataset, an agent needs more context to use the result 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 tool has zero parameters, so the schema is trivially complete. The description does not need to explain parameters; the baseline of 4 applies. It adds context about the scope ('all candidate stocks') which is helpful but not parameter-related.

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 specifies the action 'batch analysis' on a specific resource 'Stock Connect inclusion' for all candidate stocks, clearly distinguishing it from the single-stock get_stock_inclusion sibling. It is specific and unambiguous, though it doesn't elaborate on what the analysis entails.

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

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

The description provides no guidance on when to use this tool versus alternatives like get_stock_inclusion. It implies a batch scope but does not explicitly state when to prefer it, nor does it mention any 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 are provided, so the description carries the full burden. It only states what data is returned (first-day closing price) but does not disclose whether the operation is read-only, any side effects, potential errors, or the return format. For a data retrieval tool, this is a significant 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 extremely concise (one sentence) but under-specified. It lacks essential information about usage, parameters, and return values. While brevity is good, this is not appropriately sized because it fails to cover required guidance.

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 should explain what the agent can expect. It does not mention whether the response is a single value, a time series, or the unit of the price. It also lacks any context on when to use this tool among the many stock-related siblings.

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

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

Schema description coverage is 0%, so the description must compensate for the parameter meaning. It does not explain what 'stock_code' is, its format (e.g., ticker symbol, numeric ID), or how it should be provided. The schema only says 'Stock Code' with no further context, leaving the agent to guess.

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 clear purpose: 'First-day closing price for a single stock.' It specifies the resource (single stock) and the data point (first-day closing price), which is specific enough to distinguish from many sibling tools like get_stock_ohlc or get_dual_listing_price, 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?

There is no guidance on when to use this tool versus alternatives. It does not mention prerequisites, limitations, or scenarios where a different tool would be appropriate. The description provides no context 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?

No annotations are provided, so the description carries the full burden of explaining behavior. It only describes the data contents, not what the tool returns, whether it is read-only, how pagination works, or how the 'result' parameter affects the response. This leaves important behavioral expectations 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?

The description is very brief and economizes words, which is good, but it is more of a fragment than a structured definition. It conveys useful identifying information yet could include a short sentence about parameters or filtering without becoming bloated.

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

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

With no output schema, no annotations, and no parameter descriptions, the description leaves several operational gaps: what the return format is, how the result filter works, and whether limit has any upper bound. The tool is simple, but even simple tools need at least one clarifying sentence beyond a data-content listing.

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, but it only mentions 'result' as a data field and makes no clear connection to the 'result' input parameter. The 'limit' parameter is not explained at all, leaving the agent to guess whether it controls page size, result count, or something else.

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 resource type ('HKEX listing hearing records') and enumerates the key data contained (company, date, result, market), which clearly distinguishes it from sibling tools like get_listing_day_close or get_corporate_actions. It lacks an explicit verb like 'get' or 'list', but that is somewhat supplied by the tool name, making the purpose understandable.

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 guidance about when to use this tool versus any of the many sibling tools, nor any indication of filters, common use cases, or exclusions. The intended use is only implied by the domain-specific name and one-line description, which is insufficient for disambiguating among the large sibling set.

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 of behavioral disclosure, but it only says 'time series.' It does not disclose ordering, date coverage, pagination, the effect of limit, or whether values are raw or adjusted, leaving the response semantics largely unknown.

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 single sentence is free of filler and front-loads the core result type. It is appropriately short, though it is so minimal that it leaves no room for the behavioral or routing details the tool needs.

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 two-parameter tool with no annotations and no output schema, the return shape and the limit parameter are essential but unexplained. An agent would need to guess what the time-series response looks like and how to discover a valid indicator_id, possibly through get_macro_indicators.

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 by explaining the parameters. It clarifies that indicator_id identifies a single indicator, but it does not explain limit or its default of 200, leaving the optional parameter effectively undocumented.

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

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

The description states that the tool returns time-series data for a single macro indicator selected by id, which differentiates it from list-style siblings like get_macro_indicators. It lacks an explicit verb like 'returns' and the phrase 'data center' is somewhat ambiguous, but the resource and scope are generally 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?

No when-to-use guidance is provided. The description never mentions get_macro_indicators as the way to obtain an indicator_id or states when this tool should be selected over other macro or stock-data siblings. The only implicit signal is 'by id,' which is too weak to route an agent confidently.

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 full burden. It provides no information about return format, pagination, performance, or side effects. The phrase 'data center macro indicators' gives no behavioral insight; the agent cannot predict what will happen when calling 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 concise sentence with no redundant phrasing. It front-loads the core resource and immediately mentions the optional filters. It is efficient, though very brief.

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 annotations, no output schema, and a sparse description, the tool is inadequately specified for an agent. It does not explain what data is returned, how to use the filters effectively, or how it relates to siblings like get_macro_indicator_data or get_macro_tags. The agent would likely need to probe the tool to understand it.

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

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

The description says the data is 'optionally filtered by tag/source/search', which confirms these parameters are filters. This adds meaning beyond the schema, which only lists names and defaults. However, it does not explain each parameter's accepted values or behavior, and with 0% schema coverage, more detail would be expected.

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 resource is 'data center macro indicators' but does not specify what exactly is returned (list, values, etc.) or how it differs from siblings like get_macro_indicator_data or get_macro_tags. While it is not a tautology, it is vague and leaves the agent unsure of the tool's 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?

No guidance is provided on when to use this tool versus alternatives. The description only mentions optional filters, but does not explain any context such as when filters are needed or how this compares to related macro tools. The agent is left to infer 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?

With no annotations, the description carries the full burden of behavioral disclosure, but it reveals almost nothing about behavior. It only states a category of tags; it does not describe the return format, whether tags are static or dynamic, how they can be used, or any side effects (though it is likely a read). The phrase 'Data center' adds no clarity on output behavior.

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

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

The description is a single fragment without a main verb. While it is very short, it is under-specified rather than concisely complete. It does not front-load an action statement; it merely labels a concept. The lack of any structuring (e.g., a sentence) makes it less useful than a terse but complete sentence.

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

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

Given no output schema and no annotations, the description should at least clarify what the tags are and how they relate to other macro tools. It does not explain the practical purpose of the returned tags, whether they are fixed, or how they would be used with get_macro_indicators or get_macro_indicator_data. For an agent deciding whether to call this tool, the context is insufficient.

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

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

The tool has zero parameters (schema properties are empty), and the schema description coverage is 100% (nothing to cover). Per the rules, a 0-parameter tool has a baseline of 4. The description does not need to explain parameters since there are none, and it does not introduce any conflicting parameter information.

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 is a noun phrase rather than a verb+resource statement. It names the resource as 'macro indicator tags' and gives examples (growth, inflation, AI chain), which implies the tool returns a list of such tags. However, it does not explicitly state an action like 'returns' or 'lists', and the phrase 'Data center' is ambiguous. It is not a tautology but lacks a clear verb and does not differentiate from siblings like get_macro_indicators or get_macro_indicator_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?

No guidance is provided on when to use this tool versus alternatives such as get_macro_indicators or get_macro_indicator_data. The description does not mention any exclusions, prerequisites, or context for selection. An agent would have to infer that this tool likely provides tag taxonomy rather than raw data, but that is not explicitly stated.

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

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It only states that the tool provides 'insights, trends, and aggregate analysis' without explaining what data sources are used, whether the operation is read-only, what time ranges are covered, or what the response structure looks like. This is insufficient for an agent to predict the tool's behavior.

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

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

The description is very short and contains no filler or redundant wording. It front-loads the key qualifier 'Cross-IPO' and lists the main outputs in a compact phrase. However, it is arguably under-specified, which slightly reduces the value of its brevity.

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 must explain what the tool returns and how it behaves. It does not describe the return format, the specific metrics or trends included, the time period, or how this differs from related market-level tools. An agent would struggle to know whether this tool satisfies a user's request without additional investigation.

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

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

The tool has zero parameters and the schema is empty, so there are no parameter semantics to explain. Per the baseline for zero-parameter tools, the description does not need to compensate for parameter documentation. The description adds some domain context, which is sufficient given there is nothing to configure.

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

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

The description names a resource ('market insights, trends, and aggregate analysis') and the 'Cross-IPO' qualifier suggests a market-level scope, which loosely distinguishes it from stock-specific siblings. However, it is a noun phrase without a clear verb like 'retrieves' or 'returns', and the terms 'insights' and 'trends' are vague. An agent would know the general domain but not exactly what data or analysis is provided.

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

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

No guidance is given about when to use this tool versus the many sibling tools such as get_stock_overview, get_macro_indicators, or get_homepage_stocks. The 'Cross-IPO' wording implies aggregate market analysis, but there is no explicit statement of intended use cases, exclusions, or alternatives. The agent must infer usage from the name and 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?

With no annotations present, the description carries the full burden and it does disclose some behavioral traits: the ordering ('ordered by listing date desc') and the optional year filter. But it omits other operationally relevant details such as data source, result size, pagination, or auth requirements.

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, information-dense sentence that front-loads the key output fields and wraps up with the filter and ordering. The '?year' notation is slightly informal, but overall it is compact and scannable.

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

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

Given there is no output schema and no annotations, a short description should still convey what a caller will get back and how the year filter behaves. This description leaves terms like 'hit rate' undefined, does not say how many records are returned, and gives no indication of the output 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?

The schema has 0% description coverage for the single 'year' parameter. The description adds that it is an 'Optional ?year filter', which is useful, but it does not clarify whether the year applies to listing date, allotment date, or something else, nor what the default 0 means.

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 deliverable ('Oversubscription + frozen capital + hit rate') and a clear scope ('all stocks with allotment data'). However, it does not explicitly distinguish itself from sibling tools like get_allotment_result or get_allotment_tiers, so it stops short of a full 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?

No guidance is provided on when to choose this tool over the nearly-related allotment siblings, nor are any exclusions or alternative tools mentioned. The description only implies a general use case through its scope clause.

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 communicates that the tool returns a composite prediction payload rather than a single metric, which is useful, and implies a read-only operation. It does not describe response format, error behavior, or any special constraints, but for a simple get tool this is adequate.

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 compact, front-loaded sentence with a parenthetical list of contents. Every phrase contributes meaning, and there is no filler or repetition.

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

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

Given no annotations and no output schema, the description still covers the essential selection context: it names the input, the categories of data returned, and the page it feeds. It is slightly incomplete only in not disambiguating from close siblings or noting error/format behavior, but for a single-parameter get this is a minor gap.

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

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

Schema description coverage is 0% and there is one parameter, stock_code. The description only restates that the data is 'for a stock,' adding no format guidance, examples, allowed values, or clarification of what a valid stock_code looks like. The property name is self-explanatory, but the description does not compensate for the missing schema documentation.

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

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

The description states a specific verb-plus-resource ('Full default-parameter prediction data for a stock') and enumerates the payload contents (actual tiers, AI alpha map, prediction grid, agent ratings), making its purpose clear. It does not explicitly contrast with siblings like predict_allotment or get_agent_grid, but the 'prediction page' anchor helps distinguish it.

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 phrase 'backing the prediction page' implies a concrete use case, and 'full default-parameter prediction data' suggests this is the comprehensive read for prediction information. However, it gives no explicit when-to-use or when-not-to-use guidance and names no alternatives, leaving the agent to infer from sibling names.

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 behavioral disclosure. It clearly indicates a data-retrieval operation and details the returned content, but it does not explicitly state read-only behavior, error handling, pagination, locale effects, or any operational caveats. This is adequate but not fully transparent.

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 tool's core purpose and then uses a structured colon-and-list format to enumerate relevant content areas. It is somewhat dense, but every listed item contributes to the agent's understanding of what the prospectus data includes.

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 must do substantial work. It thoroughly describes the returned data, but it leaves usage boundaries, parameter semantics, and behavioral caveats mostly implicit. It is sufficient for selecting the tool but less complete for guiding a cautious 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 description coverage is 0%, so the description must compensate for parameter documentation. It only relates to the stock_code parameter through the phrase 'for a stock' and provides no detail on stock_code format or the locale parameter. The schema property names are self-explanatory, but the description adds little beyond what the schema already shows.

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 'Full prospectus info page data for a stock' and enumerates the major content areas: offer price, mechanism, greenshoe, subscription tiers, cornerstone investors, IPO financial statements, timeline, directors, syndicate, and stabilizing manager. This is specific enough to distinguish it from sibling tools like get_cornerstone_ranking, get_financial_data, and get_underwriter_ranking.

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 phrase 'Full prospectus info page data' implies the tool is for retrieving a complete prospectus dataset, and the content list gives context on what it covers. However, it does not explicitly say when to use this tool instead of narrower sibling tools, nor does it state exclusions such as 'for just cornerstone rankings, use get_cornerstone_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?

With no annotations, the description carries the full burden of behavioral disclosure. It only states the high-level purpose and says nothing about what the output looks like, whether it is a ranking or raw comparison, how data is aggregated, or any limitations. This is minimal behavioral information.

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

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

The description is a single, front-loaded sentence with no filler. The parenthetical translation adds precise context without bloating the text. 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 zero-parameter tool, the invocation contract is complete (no arguments needed). However, the description gives no sense of the return value shape—whether 'performance comparison' means a ranking table, metrics, or narrative—and with no output schema, this omission could cause an agent to call it for the wrong purpose. Given the low complexity, a 3 is appropriate.

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

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

The tool has zero parameters, so the input schema already covers everything (vacuously). No parameter explanations are needed, and the baseline of 4 applies because the description cannot add meaning where there are no 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 states a specific verb-resource combination: 'performance comparison' of 'Registrar ... across IPOs.' The Chinese parenthetical clarifies the domain. However, it does not distinguish this from the closely named sibling get_registrar_research, so it lacks the full discriminative power 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?

No guidance is provided about when to choose this tool over the many similar comparison/ranking siblings (get_sponsor_ranking, get_underwriter_ranking, get_registrar_research, etc.). There are no exclusions, alternatives, or context cues, leaving selection entirely 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether this is a read-only operation, what data it returns, whether it requires parameters, or any side effects. The phrase 'historical research and insights' hints at a read operation but does not disclose behavior such as pagination, date ranges, or output format.

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 short, which is concise, but it is under-specified rather than efficiently informative. It is a single noun phrase that does not earn its place because it adds little beyond the tool name. It is not structured with front-loaded action or context.

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 no parameters and no output schema, the description is the only source of context. It fails to explain what 'registrar historical research and insights' actually means, what kind of data is returned, or how it relates to the many sibling tools. An agent cannot determine what this tool does or when to invoke it.

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

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

The tool has zero parameters, so the schema is trivially complete. The description does not need to explain parameter semantics because there are none. Baseline 4 is appropriate for a zero-parameter tool.

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 'Registrar historical research and insights' is a noun phrase, not a verb phrase. It does not state what action the tool performs (e.g., retrieves, lists, fetches). It names a resource ('registrar historical research and insights') but lacks a specific verb, making it vague. It also does not distinguish it from the sibling tool 'get_registrar_analysis', which likely covers similar ground.

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

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

No guidance is given on when to use this tool versus alternatives. The sibling list includes 'get_registrar_analysis', which sounds closely related, but the description does not explain the difference or when to choose one over the other. The context is entirely implied by the name and the vague noun phrase.

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 does not state whether this is a read-only operation, what the response format is, whether any filtering or aggregation is applied, or what 'scatter plot data' means structurally (e.g., arrays of points, axes, series). The description is too thin to inform the agent about side effects or output behavior.

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

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

The description is a single short sentence with no wasted words, which is good. However, it is under-specified rather than efficiently concise: it omits the action verb and any context that would help an agent decide to call it.

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 tool with no output schema and no annotations, the description should at least clarify what the scatter plot data represents, how it is structured, and when it is relevant. The current description only names the plot variables, leaving the agent with insufficient context to confidently invoke the tool and interpret its result.

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

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

The tool has zero parameters, so there is no parameter semantics burden on the description. The schema already fully covers the parameter space (100% coverage with no properties), and the description correctly implies a fixed, parameterless data retrieval.

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

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

The description names a specific resource ('Oversubscription vs first-day P&L scatter plot data') and implies a retrieval verb, so an agent can roughly tell it is a data-fetching tool. However, it does not explicitly state an action like 'get' or 'retrieve', and it does not distinguish itself from the many sibling get_* tools beyond the unique resource name.

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

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

No guidance is given about when to use this tool versus alternatives such as get_oversub, get_prediction, or get_market_insights. The description only names the data content, leaving the agent to infer the appropriate context from the resource name alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'rankings' but does not disclose what the output looks like, how rankings are computed, whether they are sorted, or any limitations. For a 0-param tool, this is minimal but still leaves behavioral expectations unspecified.

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, efficient sentence with no filler. It front-loads the resource ('sponsor institution rankings') and the criterion ('by IPO involvement'). Every word earns its place; it is concise without being under-specified for a 0-param 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 has no parameters, no output schema, and no annotations, the description is adequate but minimal. It states the purpose clearly but does not clarify what 'sponsor institution' means or what format the ranking takes. For a simple 0-param tool, this is acceptable but leaves room for the agent to misjudge the result's nature. A bit more detail on the ranking criteria or output would improve completeness.

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

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

The tool has 0 parameters, and the schema coverage is 100% (vacuously). There is nothing for the description to add about parameters. Per the guidelines, a baseline of 4 is appropriate for tools with no 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 states a specific verb ('get') and resource ('sponsor institution rankings') with a clear criterion ('by IPO involvement'). It distinguishes from sibling tools like get_underwriter_ranking or get_buyback_ranking by using the specific term 'sponsor institution', though it doesn't explicitly contrast itself with them. The purpose is clear and unambiguous for an agent.

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

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

No guidance is given on when to use this tool versus the many sibling ranking tools (e.g., get_cornerstone_ranking, get_stabilizing_ranking). The description implies use when sponsor institution rankings are needed, but it does not state any exclusions or alternatives. An agent has to infer the appropriate context from the name alone.

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

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

With no annotations, the description carries the full burden, but it only says 'rankings by IPO involvement.' It does not disclose whether this is a sorted list, how the ranking is computed, what fields are returned, or any access/limitation details.

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

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

At five words, the description is extremely short, but this is under-specification rather than efficient structure. It is a fragment without a verb, so it does not form a complete instruction for the agent.

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

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

Although the tool is simple (no parameters, no output schema), the description still omits basic behavioral information and any differentiator from the many ranking siblings. An agent would have to guess what 'stabilizing manager rankings' means and what the returned data looks like.

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

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

The tool has zero parameters, so the baseline is 4. The phrase 'by IPO involvement' provides a meaningful hint about the ranking criterion, even though there are no parameter details to clarify.

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

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

The description names the resource ('stabilizing manager rankings') and the criterion ('by IPO involvement'), so an agent can infer the general subject. However, it is a noun phrase rather than a statement with a verb, and it does not differentiate this from sibling ranking tools such as get_underwriter_ranking or get_sponsor_ranking.

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 guidance on when to use this tool or which alternative to prefer. Given the large sibling set of ranking tools, an agent receives no context for selecting this over get_buyback_ranking, get_cornerstone_ranking, etc.

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

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

With no annotations, the description carries the full burden. It does disclose the output contents (grouped by headline category, with publish date and file URL), which is useful. However, it does not mention any limitations (e.g., date range, pagination, or whether all historical announcements are included) or side effects, leaving gaps for a mutation-free retrieve tool.

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

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

The description is a single, front-loaded sentence with zero waste. It states the core purpose and key output attributes immediately, making it easy to parse.

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

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

Given no output schema and no annotations, the description provides the essential purpose and output shape (grouped announcements with date and URL). However, it omits details like the exact return structure (e.g., how categories are organized), any filtering options, or prerequisites. It is minimally sufficient but not comprehensive.

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 that stock_code identifies the stock ('for one stock'), but it does not explain the locale parameter or its default (zh-CN). The description adds only partial meaning, leaving locale behavior 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?

The description clearly states the verb (get) and resource (HKEXnews announcements for one stock), including details about grouping, publish date, and file URL. It is specific enough to distinguish itself from sibling tools like get_stock_buyback or get_stock_ccass, 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?

No guidance is provided on when to use this tool versus alternatives. The description only mentions 'for one stock,' implying it requires a stock code, but there is no note about when to prefer it over similar tools like get_stock_disclosure or get_corporate_actions.

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

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

With no annotations, the description carries the burden. It discloses ordering ('newest first'), granularity ('per-day shares/amount'), and aggregation ('aggregate totals'), which is useful. However, it does not disclose pagination limits, date range behavior, or whether the data is historical or real-time, leaving some behavioral gaps.

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

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

The description is compact and front-loaded with the key purpose ('回购明细 (per-stock buyback)'), followed by ordering and aggregation details. It is a single sentence with no wasted words, though the bilingual phrasing adds a slight 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?

For a simple 2-parameter tool with no output schema, the description covers the core purpose and data shape. However, it lacks details on response structure, pagination, and the meaning of 'locale', which an agent might need to invoke it correctly in different contexts.

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 explains the resource (per-stock buyback) but does not explain the 'locale' parameter or the format/meaning of 'stock_code' beyond the schema's title. The description adds context about the output but not about the parameters themselves.

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: 'share buyback records for one stock' with ordering and aggregation details. It distinguishes from siblings like get_buyback_ranking (which is ranking-focused) by emphasizing per-stock detail, though it doesn't explicitly name the sibling.

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 retrieving per-stock buyback details, and the 'newest first' ordering gives a sense of the data shape. However, it does not explicitly state when to choose this over get_buyback_ranking or other buyback-related tools, nor does it mention any prerequisites or 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the data categories returned but does not disclose whether this is a read-only operation, whether it requires any special permissions, what the output format is, or whether the data is historical/current. For a data-retrieval tool this is a moderate gap, but the description does at least clarify the scope of the 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 a single concise sentence that front-loads the resource and then lists the data dimensions. It is efficient and readable, though it could be slightly more structured by separating the core purpose from the data breakdowns.

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 one parameter, no output schema, and no annotations, the description is thin. It tells the agent what data is returned but not how to invoke it correctly (stock_code format), what the output looks like, or when to prefer it over sibling tools. The tool is simple, but the description still leaves important gaps for an agent deciding whether to call it.

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

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

Schema description coverage is 0%, and the description does not explain the stock_code parameter beyond its name. The description implies the tool is per-stock, but it does not specify the expected format (e.g., numeric code vs. string, HKEX format, leading zeros). With only one parameter, the description should have compensated by explaining what stock_code means and how it should be formatted.

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 ('get') and resource ('CCASS custodian demographics for a stock') and enumerates the dimensions covered (type, province, gender, age distributions, HK letter/era breakdowns). It is clear what the tool returns, though it does not explicitly distinguish itself from siblings like get_registrar_analysis or get_allottee_profile, which may also relate to shareholder/custodian 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?

No guidance is given on when to use this tool versus alternatives. The sibling list includes several potentially overlapping tools (get_registrar_analysis, get_allottee_profile, get_stock_overview), but the description does not mention any of them or provide selection criteria. The only implied usage is that it applies to a stock identified by stock_code.

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 disclose useful behavioral details: records are returned 'newest first' and include specific fields. However, it does not mention whether results are paginated, how the locale parameter affects output, or what happens when a stock has no records. It provides some transparency but not comprehensive behavioral 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 a single, tightly written sentence that front-loads the tool's purpose in Chinese and English, then lists the distinguishing output attributes. There is no filler or redundant repetition of the tool 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 simple read-only lookup tool, the description covers the main purpose and output fields, and with no output schema that field list is valuable. However, given no annotations and no output schema, it still lacks explanation of the locale parameter, stock_code format, and return container, so it is only minimally 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 description coverage is 0%, so the description must compensate for the undocumented parameters. It only implicitly identifies stock_code as the stock selector ('for one stock'); the locale parameter is never explained, and no format or example is given for stock_code. This is insufficient for two parameters with zero schema documentation.

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

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

The description uses a specific verb-resource pattern ('DI records for one stock') and clearly distinguishes this tool from its likely sibling get_disclosure_interest by emphasizing 'per-stock' scope. It names the key output fields (holder, capacity, event type, shares, pct), leaving no doubt about what the tool returns.

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 phrase 'for one stock' provides clear context: this is the tool to use when you need disclosure-of-interest records for a single stock. It does not explicitly name alternatives or say when not to use it, but the per-stock scoping is enough to route an agent correctly among the sibling list.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It hints at multi-period data ('across review periods') but does not explain what 'detail' includes, whether it returns current or historical status, or what the response looks like.

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 filler or repetition. It front-loads the single-stock scope, though it is terse to the point of under-specification.

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 should at least state what the returned detail contains and how to format stock_code. It does neither, leaving an agent with only a vague sense of the tool's purpose.

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

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

Schema description coverage is 0%, and the description does not mention stock_code at all. The parameter name is self-explanatory, but the description fails to clarify the expected format, such as leading zeros or exchange-specific code conventions.

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 the resource ('Stock Connect inclusion detail') and scope ('single-stock', 'across review periods'), which is clear enough to distinguish it from batch-oriented siblings like get_inclusion_batch. It lacks an explicit verb, but the tool name supplies the action.

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 guidance on when to use this tool versus alternatives. 'Single-stock' implies a scope but does not explicitly contrast with get_inclusion_batch or state when not to use this tool.

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

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

With no annotations, the description carries the transparency burden. It does disclose non-obvious behavior: the output is AI-generated and offered in zh/en. However, it does not explain how the language variant is chosen, whether the narrative is deterministic, or what output shape to expect.

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

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

The description is a single compact sentence with no filler. It front-loads the core idea 'AI-generated narrative' and includes the language and subject scope without redundancy.

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

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

For a low-complexity, one-parameter read tool, the description conveys the output nature and domain, which is minimally viable. But without an output schema or annotations, it leaves open the code format and language-selection behavior, so it is not fully 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 description coverage is 0%, so the description must clarify the single stock_code parameter. It only says 'a stock's IPO characteristics' and does not specify the code format, market, or accepted values; the parameter name itself is doing most of the semantic work.

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 the deliverable as an AI-generated narrative in Chinese/English summarizing a stock's IPO characteristics, which is specific enough to distinguish it from related tools like get_stock_overview or get_prospectus. It lacks an explicit action verb, but the tool name supplies 'get' and the resource is clearly described.

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

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

No guidance is given on when to use this tool versus the many sibling tools such as get_stock_summary, get_prospectus, or get_stock_overview. The only implied trigger is needing a narrative about IPO characteristics, but no exclusions or alternatives are named.

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

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

Annotations are absent, so the description carries the full behavioral transparency burden. It discloses the data frequency and source but says nothing about error handling, required stock code format, return structure, or any side effects. This is inadequate for a tool that will be invoked programmatically.

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 that front-loads the most important attribute (OHLC data) and includes a useful time-range qualifier. 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 tool has one parameter, no output schema, and no annotations, the description should at least clarify the stock_code format and the shape of the returned data. It only says 'data' without specifying fields like open/high/low/close/volume or response type. The missing parameter format is a critical gap 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?

The only parameter, stock_code, is a bare string with zero schema description. The description does not explain accepted formats (e.g., '600519' vs 'SH600519'), examples, or constraints. With 0% schema coverage, the description adds no value for 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 clearly identifies a specific resource: daily OHLC candlestick data with a ~400-day range from Tencent Finance. While it doesn't explicitly contrast with siblings, no other sibling tool name references OHLC, so the purpose is unambiguous. A minor gap is the lack of a verb, but the tool name supplies it.

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

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

The description provides no guidance on when to use this tool versus sibling data tools like get_stock_overview or get_stock_summary. There is no mention of preferred contexts, prerequisites, or alternatives, leaving the agent to guess which tool fits a query.

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 disclose meaningful behavior: it returns ok:false for unknown stock codes and clarifies that the data.s.reallocation flag means discretionary reallocation, potentially disagreeing with get_allotment_result. It doesn't cover permissions, rate limits, or data freshness, but the error behavior and semantic caveat are substantive.

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 component list, followed by error behavior and a caveat. Every sentence adds information, though 'plus cross-market context' is slightly vague. Overall it is well-structured with no filler.

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

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

For a single-parameter analysis tool with no output schema, the description covers the main output components, the failure mode, and a key semantic warning. It lacks stock_code format details and usage routing, but it is largely sufficient for an agent to invoke the tool correctly.

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

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

The single stock_code parameter has 0% schema coverage, and the description adds no format, example, or accepted-value guidance. The parameter name is self-explanatory, but the description does not compensate for the missing schema documentation.

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

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

The description clearly identifies the resource as 'per-stock IPO analysis' and enumerates its components (subscription rates, allotment tiers, PnL scenarios, CCASS demographics, narrative, cross-market context). It lacks an explicit verb and doesn't contrast with sibling tools like get_allotment_result or get_stock_narrative, but the scope is unambiguous.

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

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

No guidance is provided on when to use this tool versus alternatives. The only sibling mention is a caveat about data disagreement with get_allotment_result, not a routing rule. The 'Full per-stock IPO analysis' label implies a comprehensive use case, but exclusions and alternative selection criteria are absent.

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 load. It explicitly discloses the failure mode (ok:false for unknown/no data) and explains a nuanced field (summary.reallocation) that might otherwise be misinterpreted. It doesn't cover auth or rate limits, but for a read-only summary tool these are less critical.

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 ('Lightweight stock summary...') and kept reasonably short. The field note, while a bit long, contains essential caveats that earn their place. The structure is clear and easy 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?

With no output schema and no annotations, the description should describe the return shape to be self-sufficient. It only mentions 'key stats', 'tier classification', and the single summary.reallocation field, leaving the rest of the response unspecified. An agent can call the tool with just a stock code, but cannot anticipate the full result structure, making it incomplete.

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

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

The schema has one parameter, stock_code, with only a type and title (0% description coverage). The description mentions 'stock code' in the error context but does not explain expected format, examples, or origin. With no schema help, the description fails to add meaningful parameter semantics, so agents must guess.

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

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

Description clearly states it returns a 'lightweight stock summary' with 'key stats and tier classification', which is a specific resource and purpose. It doesn't explicitly contrast with sibling tools like get_stock_overview, but the 'tier classification' feature helps distinguish it. The purpose is clear enough for an agent to identify what it does.

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 a targeted alternative for one field: 'For the raw clawback/重新分配 flag from the allotment PDF, use get_allotment_result instead'. It also notes the ok:false behavior for unknown codes. However, it lacks general guidance on when to choose this tool over other stock data tools, so usage context is only partially covered.

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 carry behavioral disclosure. It only notes pagination and the type_key filter, but does not mention read-only nature, authentication, rate limits, or response structure. Minimal behavioral information is provided.

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 and front-loads the purpose. Every word earns its place, though it is so brief that it sacrifices necessary 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?

For a tool with 5 parameters, no output schema, and no annotations, the description is inadequate. It does not explain return format, the meaning of days or locale, or provide any context about expected input ranges. An agent would struggle to call it correctly.

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

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

Schema description coverage is 0%, so the description must explain parameters. It explains type_key values and implies pagination, but days, locale, page, and page_size are left to interpretation. Incomplete parameter documentation.

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

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

The description clearly states it lists trading suspension/resumption announcements and mentions pagination. It is specific about the resource and action, though it does not explicitly differentiate from sibling tools like get_stock_announcements.

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

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

No guidance on when to use this tool vs alternatives. It does not mention any context or exclusions, leaving the agent to infer suitability from the name and description alone.

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

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

With no annotations, the description carries the full burden. It does disclose the ranking criterion (IPO involvement), but it doesn't state sort direction, ranking period, data source, or whether the result is a full list versus top N. It is minimally transparent for a read-only zero-argument 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 one short phrase with no filler or repetition beyond the tool name. It front-loads the core meaning, though it is so terse that it sacrifices some helpful context.

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 no-argument tool with no output schema or annotations, the description identifies what is ranked and by what criterion, which is probably enough to invoke it. However, it doesn't convey the shape of the returned ranking, ordering convention, or temporal scope, so an agent cannot anticipate the output fully.

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

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

The tool has zero parameters and the schema coverage is effectively complete (empty properties object), so there is no parameter detail the description must compensate for. Per the baseline for parameterless tools, this is satisfactory.

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

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

The description names the resource ('underwriter institution rankings') and the specific basis ('by IPO involvement'), which is clear enough to distinguish it from sibling ranking tools such as get_buyback_ranking or get_sponsor_ranking. It lacks an explicit verb/retrieval phrasing, but the noun phrase still conveys the tool's 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 gives no indication of when to prefer this tool over sibling ranking tools, nor any exclusions such as time frames or data availability. The only implied guidance is 'when you need underwriter rankings', which basically restates the 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the content type (8-K filings) but does not disclose whether the tool is read-only, how it handles pagination (the limit parameter implies a cap), whether it requires date ranges (start/end), or what the response structure looks like. For a data-retrieval tool with no annotation safety profile, this is a significant omission.

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

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

The description is a single sentence with no wasted words. It front-loads the core purpose ('US corporate actions (8-K)') and then lists examples, which is efficient. However, given the tool's complexity (5 parameters, no annotations, no output schema), the brevity becomes under-specification rather than conciseness, but the sentence itself is well-structured and earns its place.

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

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

The tool has 5 parameters, no output schema, no annotations, and numerous closely related siblings. The description covers only the basic purpose and examples, omitting parameter usage, output format, pagination, and differentiation from siblings. This is highly inadequate for an agent to invoke the tool correctly without further investigation.

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

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

Schema description coverage is 0%, and the description provides no explanation of any parameters. The five parameters (end, limit, start, ticker, action_type) are not mentioned at all, leaving the agent to guess that start/end are date bounds, limit controls result count, and ticker/action_type filter results. This is a complete failure to compensate for the missing 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 retrieves US corporate actions, specifically 8-K filings, and lists examples like M&A, earnings, dividends, splits, and buybacks. This makes the purpose unambiguous and distinguishes it from siblings like get_corporate_actions (which likely covers broader regions) and get_earnings_calendar (focused on earnings). The verb 'get' implies retrieval, and the resource is well-defined.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention that it is US-specific, nor does it suggest using get_corporate_actions for non-US actions or get_earnings_calendar for earnings-only queries. There are no exclusions or contextual clues for selecting this tool over similar ones, leaving the agent to infer usage from the name and examples alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The single phrase 'US IPO / SPAC new listing calendar' conveys almost nothing about behavior: it doesn't state whether the tool is read-only, what the response format is, how filtering works, or any side effects. There is no mention of pagination, performance, or required permissions. This is a severe gap 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 extremely short, which is concision, but it is not structured or front-loaded with useful information. It is a single noun phrase that lacks any actionable content. While brevity is a virtue, under-specification is a flaw here; there is no effort to lead with the most important details, and the description is both vague and unhelpful.

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 absence of annotations, output schema, and parameter descriptions, the description is drastically incomplete. An agent cannot determine what the tool returns, how to interpret the output, when to use it, or what parameters mean. For a relatively simple tool with two optional parameters, this could be explained in a sentence or two, but the current description falls far short of that.

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

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

Schema description coverage is 0%, and the description says nothing about the 'limit' or 'status' parameters. The parameter names are suggestive but not definitive (e.g., 'status' could mean IPO status, listing status, or something else). The agent cannot know what values to pass for 'status' or how 'limit' affects results. Since the schema provides no descriptions and the tool description does not compensate, this is a critical deficiency.

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 resource (US IPO / SPAC new listing calendar) but does not state an explicit verb or action. It is clear that this tool relates to US listing calendars, but it doesn't specify what is returned (e.g., dates, companies, statuses) or whether it covers upcoming or historical listings. It is distinguishable from siblings like 'get_earnings_calendar' by the IPO/SPAC focus, but the wording is a noun phrase rather than a proper purpose statement.

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

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

There is no guidance on when to use this tool versus the many sibling tools (e.g., get_listing_hearings, get_corporate_actions, get_earnings_calendar). The description does not mention any preconditions, typical use cases, or exclusions. An agent has to infer when this tool is relevant, which is especially risky given the large sibling set.

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 carry the full behavioral burden. It mentions the source and output fields, but does not disclose pagination, return format, or the effect of the limit parameter (default 200), which is especially important given the 'all HK-listed companies' wording.

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 fields; each sentence adds information. It is slightly telegraphic but contains 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?

For a simple two-parameter list tool, the description conveys the domain and fields, and the absence of an output schema is partially mitigated by listing the fields. However, limit behavior, pagination, and differentiation from sibling search/list tools remain unaddressed.

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 explains 'search' as an optional substring search, but 'limit' is left entirely to the schema's name/default with no context about maximum values or pagination.

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

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

The description clearly states a specific resource ('all HK-listed companies'), the source ('full-market securities master'), and the returned fields (code, zh/en name, board, isin, listing_date). The HK scope distinguishes it from generic siblings like list_stocks or search_stocks.

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 purpose and optional substring search imply when to use it (browsing all HK companies or filtering by name), but the description does not explicitly say when to prefer this over siblings such as search_stocks or list_stocks, nor does it state any exclusions.

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

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

No annotations are present, so the description carries the full burden of behavioral disclosure. It states an action (list) but does not mention whether this is a read-only operation, whether it requires authentication, or any potential limitations such as pagination or data freshness. The phrase 'tracked IPO stocks' implies a subset but does not explain what 'tracked' 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?

A single, efficient sentence that front-loads the purpose and includes the key return fields. No filler or redundancy.

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

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

For a simple list tool with no parameters, the description states the output fields. However, it does not clarify pagination behavior, ordering, whether the list is exhaustive, or how frequently it updates. Given no output schema, a bit more context (e.g., pagination or time range) would round it out, but it is largely sufficient for a basic list.

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

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

The tool has zero parameters, so the schema is trivially complete. The description adds no parameter-specific meaning, but none is needed. Per the rules, a baseline of 4 applies when there are no 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 states a clear verb and resource ('List all tracked IPO stocks') and specifies the fields returned (code, name, listing date). It is immediately distinguishable from sibling tools like search_stocks (which implies search/filter) and list_hk_companies (which is broader 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?

No guidance is provided on when to use this tool versus alternatives. With many sibling tools (search_stocks, get_homepage_stocks, etc.), the description does not mention any exclusions or conditions that would help an agent decide between them.

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. It adds real value by disclosing the default fallback behavior (alpha=None and oversub=None) and the return shape ('Pool A/B tier expected lots and hit pct'). It does not discuss side effects or auth, but 'Predict...Returns' strongly implies a read-only computational operation.

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 terse sentences: a front-loaded purpose statement, a defaults clause, and a return-value clause. Every sentence earns its place with no filler or redundant restatement 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?

With no output schema, no annotations, and an empty input schema, the description must do the heavy lifting, and it mostly does: purpose, key overrides, defaults, and output are all covered. Remaining gaps are the meaning of 'agent' parameter values and what 'cibo' refers to, but for a prediction tool the core usage is 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 description coverage is 0%, so the description must compensate. It explains alpha and oversub meanings and their None defaults, which is genuinely helpful. However, the 'agent' parameter is never explicitly explained as a model selector, and stock_code is only obvious from its name, not from the description.

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 'Predict IPO allotment success' – a specific verb and resource – and narrows the scope with 'arbitrary final oversubscription multiple and allocation-method alpha'. It is clear enough to distinguish intent from retrieval siblings like get_oversub or get_allotment_result, though it never names or explicitly contrasts those siblings.

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

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

The phrase 'arbitrary final oversubscription multiple and allocation-method alpha' signals this is for custom/hypothetical scenarios, and the None-default behavior clarifies when the tool falls back to its own or cibo's predictions. It provides clear context but no explicit alternatives or exclusion 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?

The description discloses that the search is fuzzy and supports cross-script conversion via OpenCC when available. However, it does not mention what the tool returns (e.g., a list of matching stock objects), result limits, or any side effects. Since no annotations are provided, this is the only behavioral information available, and it is minimal.

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

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

The description is a single, front-loaded sentence that immediately states the action and scope. Every word adds value, with no redundancy or 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?

For a tool with one parameter and no output schema, the description covers the essential purpose and query format. However, it lacks details about the return value, such as whether it returns a list of stock objects or a summary, and does not address potential pagination or limits. Given the simplicity, it is adequate but could be more complete.

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

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

The schema only defines 'query' as a string with no description. The tool description compensates by specifying that the query can be a stock code, English name, or Chinese name, which clarifies the acceptable input format. This provides meaningful semantics beyond the raw 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: fuzzy searching stocks by code, name, or Chinese variants. This distinguishes it from sibling tools like list_stocks, which likely provides a full listing rather than a targeted search.

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

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

The description does not provide guidance on when to use this tool versus alternatives like list_stocks or get_stock_overview. It only describes what it does, leaving the agent to infer the appropriate context. No exclusions or conditions 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 carries the full burden and does reasonably well: it discloses the inputs used (KNN forecast, stamp duty, trading fee, transaction levy, FRC levy), the returned quantities (subscription amount, margin interest, expected allocated lots, total cost, break-even move/price), and the exact fallback semantics when oversub/interest_days are None. It omits permissions/auth or determinism caveats, keeping it short of a 5.

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 tight sentences, front-loaded with purpose, then derivation, then default behavior. No filler, though the tax-schedule enumeration is dense and could be trimmed since those names don't map to parameters.

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 computational tool with no output schema and no annotations, the description covers purpose, cost components, returns, and two default behaviors, which is near-adequate. It falls short on the ambiguity between fee and platform_fee and on the margin parameters, where an agent could easily misconfigure the call.

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% across 10 parameters, so the description must compensate, but it only clarifies oversub and interest_days defaults. It leaves fee (which coexists ambiguously with platform_fee), lots, use_margin, margin_rate, margin_ratio, and commission_rate undocumented, so several non-obvious parameters remain guesswork.

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+scope: 'IPO subscription cost and break-even for one stock at a given lot count.' It also explains the two-component derivation (KNN expected-lot forecast + HK sell-side tax schedule), which clearly separates it from siblings like predict_allotment or get_allotment_result.

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 by the computation described (you run it when you want the all-in cost and break-even for a subscription), but it never states when to prefer it over predict_allotment, get_allotment_tiers, or get_frozen_calendar, nor any prerequisites. The default-explanation sentences describe behavior, not tool selection.

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