gangtise-mcp

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v0.1.14
Disambiguation4/5
Most tools have clearly distinct purposes, targeting different content types (announcements, reports, meetings, etc.) and markets (A, HK, US). However, the sheer number (66) can cause confusion, and some tools like the multiple financial statement variants (e.g., balance_sheet vs balance_sheet_hk) are similar but necessary due to market differences.
Naming Consistency4/5
The naming follows a 'gangtise_<domain>_<operation>' pattern for many tools (e.g., announcement_list, announcement_download). However, exceptions like 'gangtise_lookup', 'gangtise_read_response', and 'gangtise_realtime' break the pattern, and some tools lack an explicit operation suffix (e.g., 'gangtise_balance_sheet').
Tool Count2/5
With 66 tools, the server is overloaded for an MCP server. While the scope is broad (financial data covering multiple markets and content types), this number makes selection difficult for agents and suggests the server could benefit from splitting into smaller, more focused servers.
Completeness4/5
The tool set covers a wide range of financial data needs: announcements, financial statements, K-lines, real-time quotes, research reports, opinions, meetings, knowledge base, and EDB data. Missing some minor areas like corporate actions or dividends, but overall it provides a thorough surface for financial analysis.
Average 3.3/5 across 66 of 66 tools scored. Lowest: 2.4/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 106 commits in the last 12 weeks
- No stable releases found
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description only states it queries status, which implies a read operation, but does not elaborate on behavior like polling mechanisms, possible status values, or response structure. With no annotations, more detail is needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, achieving conciseness but lacking structure. It does not front-load critical information like input requirements or return format, making it minimally viable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description is incomplete. It does not specify the return format, possible statuses, or how to interpret results. For a simple check tool, more context is necessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter 'dataId' has no description in the input schema (0% coverage), and the description does not explain its purpose or expected format. It adds no value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies the action (query) and resource (generation status of long-short debate task), clearly indicating the tool's function. However, it does not explicitly differentiate from sibling tool 'gangtise_viewpoint_debate', which likely creates the task, so a slight deduction applies.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 'gangtise_viewpoint_debate' for creating tasks. There are no prerequisites or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must cover behavioral traits. It only states it is a list query with filtering. It does not disclose read-only nature, authentication needs, rate limits, pagination behavior, or data freshness. 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with an irrelevant date instruction (30 chars) that serves a training context, not tool usage. The actual description is one sentence but buried. Not concise nor well-structured for an agent.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 11 parameters, no output schema, and no annotations, the description is insufficient. It does not explain return format, pagination, or how to use parameters together. An agent would need additional inference.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 45%, so the description should add meaning. It lists filter categories (security, industry, rating, time) but does not explain parameter formats or semantics for undocumented parameters like industryList or keyword. Only high-level guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it queries a list of overseas independent researcher opinions and supports filtering. This is a specific verb and resource. However, it does not distinguish from sibling tools like gangtise_opinion_list or gangtise_foreign_opinion_list, which may overlap in purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions filtering capabilities but provides no guidance on when to use this tool versus alternatives. No explicit context, when-not-to-use, or sibling comparisons are given, leaving the agent to guess based on the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavioral traits. It only states query and filtering capability, omitting details on pagination, rate limits, data freshness, or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Relatively concise (two lines) with a necessary date reminder. However, the front-loaded date context seems misprioritized; tool purpose would be more appropriate first.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 13 parameters, no annotations, and no output schema, the description fails to cover return format, pagination behavior, or how to use lookup-dependent fields like regionList. Incomplete for a tool of this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 46%, leaving many parameters undescribed. The description lists some filter dimensions (security, region, industry, broker, rating, time) but does not explain specifics like ratingList or ratingChangeList. Inadequate compensation for low schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it queries a list of foreign institution opinions (e.g., Goldman Sachs, Morgan Stanley) with multiple filter dimensions. Distinguishes from siblings like gangtise_foreign_report_list by focusing on opinions rather than reports.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. Does not mention when not to use it or suggest other tools for similar tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only says 'download' but does not disclose behavioral traits such as whether it is read-only, any side effects, permission requirements, or output type (e.g., file bytes vs. URL). The lack of output schema further reduces transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description includes a date context note that is not part of the tool's functionality, cluttering the purpose. The actual tool description is a single sentence, which is concise but mixed with irrelevant metadata. Every sentence should serve the tool definition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (one param, no output schema) but the description does not explain what a download entails (e.g., returns file content, requires specific permissions). It leaves ambiguity about the output and usage flow, making it incomplete for an agent to reliably invoke.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (one parameter with description). The description adds no extra meaning beyond the schema, merely restating the action. With high coverage, baseline of 3 is appropriate; no additional value is provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states '按 fileId 从 Gangtise 云盘下载文件' (download file from Gangtise cloud drive by fileId), clearly indicating the verb and resource. It distinguishes from sibling tools like gangtise_drive_list (list) and other download tools (research, summary). However, the purpose could be more explicit about the type of file being downloaded.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 vs alternatives. The only clue is the fileId parameter description mentioning it comes from gangtise_drive_list, but the tool description itself lacks explicit prerequisites, usage context, or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 only states 'download HK stock announcement file', which implies a read operation but does not describe whether authentication is required, what file format is returned, or any rate limits. The description is insufficient for an agent to understand side effects or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The actual tool description is a single short sentence, which is concise. However, a large date context note ('[当前日期 2026-05-27...]') is included, which is irrelevant to the tool's purpose and may confuse the agent. Without that note, the description would be well-structured. As is, it is cluttered.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity (1 parameter, no output schema), the description is minimally complete. It tells what the tool does but lacks details on output format (e.g., binary file vs URL), usage prerequisites, and how it fits with sibling tools. The agent may need to guess or rely on naming conventions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Parameter coverage is 100% with a single required parameter. The schema description '公告 ID，来自 gangtise_announcement_hk_list' adds meaningful context by specifying the source of the ID. The tool description itself does not elaborate on the parameter, but the schema description compensates. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description '下载港股公告文件' clearly states the tool downloads Hong Kong stock announcement files. The required parameter 'announcementId' is linked to gangtise_announcement_hk_list in its description, distinguishing this tool from siblings like gangtise_announcement_download (general) and gangtise_announcement_hk_list (list). The purpose is specific and actionable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit usage guidelines are provided. The description does not state when to use this tool over alternatives such as gangtise_announcement_download or gangtise_research_download. The parameter description hints at obtaining the ID from gangtise_announcement_hk_list, but this is not framed as a prerequisite or guideline. The date context note is irrelevant to tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must carry behavioral context. It does not disclose read-only nature, authentication requirements, rate limits, or pagination behavior (despite 'size' and 'fetchAll' parameters). Minimal behavioral info.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short but includes an irrelevant system prefix about current date, which wastes space. The substantive part is one sentence, making it concise but too brief to cover all necessary aspects.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 10 parameters, no output schema, and no annotations, the description is insufficient. It does not explain return format, pagination, authentication context ('my'), or how filters interact. The tool's completeness is low.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (some parameters have descriptions). The description adds meaning for security, institution, category, and time range filters, matching the schema's documented parameters. However, parameters like 'from', 'keyword', and 'researchAreaList' are left unexplained, and the description does not compensate fully.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries 'my conference recording list' and lists filtering options (securities, institutions, categories, time range). This distinguishes it from sibling tools like 'gangtise_record_list' by specifying 'my', but lacks explicit differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus siblings like 'gangtise_record_list' or 'gangtise_my_conference_download'. The description only states what it does, not when it is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behaviors like read-only nature, pagination, rate limits, or side effects. The date context note is helpful but insufficient for a complete behavioral picture.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is brief but front-loaded with a date context note. While efficient, it omits key usage details and could be better structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 8 parameters, no output schema, and no annotations, the description lacks completeness. It does not explain return format, pagination behavior (despite fetchAll param), or how to use queryMode and gtsCodeList effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is high (88%), so parameters are mostly explained in the schema. The description adds a date conversion note but no additional meaning for parameters like queryMode or gtsCodeList beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries AI-generated investment clue lists for stocks or industries. However, it does not differentiate from sibling tools like gangtise_investment_logic or gangtise_opinion_list, which may overlap.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The description only mentions the need for a time range, but lacks context about prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, placing the full burden on the description. The description does not disclose behavioral traits such as read-only hint, permission requirements, rate limits, or pagination behavior (though schema hints at pagination with size and fetchAll). It lacks explicit 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, consisting of a single sentence plus a necessary date/time context instruction. The instruction is front-loaded and relevant for the agent to interpret user queries correctly. It could be slightly tighter, but overall efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 8 parameters and no output schema or annotations, the description covers the basic function and filter capabilities but omits details about pagination, the from parameter, and what the output contains. It is adequate but not fully comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 75% schema description coverage, the schema already explains most parameters. The description adds a high-level overview of filter types (keyword, file type, space type, time range) but does not add significant new meaning beyond the schema. The from parameter is left undocumented in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states '查询 Gangtise 云盘文件列表' (query Gangtise drive file list) and mentions filtering capabilities, establishing a specific verb-resource relationship. However, it does not differentiate from sibling tools like gangtise_drive_download or other list tools, so it loses a point.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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, nor does it specify prerequisites or exclusion criteria. It only describes what the tool does, leaving the agent without context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description includes a practical note about the current date and timezone, which helps interpret temporal queries. However, it does not disclose that the tool is read-only, whether authentication is required, or how pagination works (though schema includes 'size' and 'fetchAll'). With no annotations, the description partially fills the gap but lacks key behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, with the date instruction front-loaded for immediate context. The second sentence states the purpose. It is not overly long, but the date instruction could be integrated into parameter descriptions to reduce repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 15 parameters, low schema coverage, and no output schema, the description is insufficient. It does not explain default behaviors, sorting, or return format. The date instruction adds some context, but overall the description leaves many gaps that an agent would need to infer or test.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description lists filter categories (research area, institution, etc.) that correspond to parameters, but provides no details on valid values, formats, or how to combine them. With only 33% schema coverage for parameters, the description should compensate, but it only adds a high-level overview, leaving many parameters underspecified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries a forum schedule list and lists filter dimensions (research area, institution, security, etc.). The name 'gangtise_forum_list' reinforces the purpose. However, it does not explicitly differentiate from sibling list tools, relying solely on the name and description context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 like gangtise_announcement_list or gangtise_drive_list. The description only states what the tool does, not when it should be preferred. This omission requires the agent to infer use cases from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description does not disclose behavioral traits such as data availability, error handling, rate limits, or any side effects beyond a basic query. The agent receives no insight into reliability or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and to the point, with only two sentences. The date context note is boilerplate but does not detract greatly. However, it could be structured to highlight key differentiators more effectively.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 7 parameters and no output schema, the description is minimal. It does not explain return format, pagination, handling of multiple periods, or how to interpret cumulative data. The presence of many closely related siblings increases the need for context, which is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond the already detailed parameter descriptions in the schema. It merely restates that filtering is supported, which is obvious.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it queries A-share income statements on a cumulative basis, and mentions supported filters. However, it does not explicitly distinguish from siblings like gangtise_income_statement_hk or gangtise_income_statement_quarterly, which are very similar in name and purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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. For example, it does not specify that this tool is for A-share stocks only, nor does it suggest siblings for other markets or reporting types.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should fully convey behavioral traits. It only states the action and return type but does not disclose side effects, authentication needs, rate limits, or output format (e.g., direct text vs. file URL). Minimal 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.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description includes an irrelevant date context note about date handling that distracts from the tool's purpose. The essential part is short but the note makes it less concise. Removing the note would improve conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and many sibling download tools, the description lacks details on return format, differences from similar tools, and prerequisites. It covers the basics but is insufficient for an agent to fully understand usage context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description does not add meaning beyond what is in the schema; it only restates the return type. No extra context on parameter formats or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool downloads conference recordings and returns ASR transcription or AI summary. The verb '下载' and resource '会议录音资源' are specific. The schema further specifies the required conferenceId and contentType, making purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. There is no mention of prerequisites, such as needing a conferenceId from gangtise_my_conference_list, which is only in the schema. No exclusions or comparisons to sibling download tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 it is a list query with filters, but fails to disclose behavioral aspects such as pagination behavior, data freshness, rate limits, or whether the operation is read-only. This is insufficient for a tool with 18 parameters.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, with a front-loaded date context note essential for accurate time-based queries. The core purpose is stated in one sentence. No unnecessary repetition, though the bracket note adds slight overhead.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the large number of parameters (18) and no output schema, the description provides a basic overview but lacks details on return format, pagination, or error handling. The schema partially compensates with parameter descriptions, but completeness is only moderate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 56% description coverage, and the description lists filter dimensions but does not add detailed semantics beyond what is in the schema. For a tool with many parameters, additional parameter-specific guidance would be beneficial, but the baseline is acceptable.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action (查询) and resource (券商研报列表), and lists supported filters. However, it does not distinguish this list tool from sibling tools like 'gangtise_research_download' or 'gangtise_research_outline', which also deal with broker research reports.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus alternatives. It lists filter options but offers no explicit conditions, prerequisites, or instructions for selecting this tool over similar siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description does not disclose pagination behavior (though fetchAll parameter exists), rate limits, or default size. It also doesn't mention what happens on empty results or invalid filters. For a tool with 15 parameters, more disclosure is needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, but opens with a date-context reminder that is more suitable for system instructions than tool description. It is concise but includes extraneous information that could confuse agents expecting pure functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 15 parameters, no output schema, and no annotations, the description fails to cover pagination, default size, response format, or filter interdependencies. The brief description leaves significant gaps for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 33%, and the tool description adds no parameter details beyond listing filter categories (e.g., 研究方向, 机构). Parameters like from, permission, objectList (with enum values in schema but not described in description) are left for the agent to infer. The description does not compensate for the schema coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states '查询策略会日程列表' (query strategy meeting schedule list), specifying the verb (查询) and resource (策略会日程列表). It distinguishes from sibling tools like gangtise_announcement_list or gangtise_roadshow_list by targeting strategy meetings specifically.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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. With many sibling listing tools (e.g., gangtise_foreign_report_list, gangtise_opinion_list), the agent lacks context for selection. The description implies filtering but does not state prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It mentions filtering but omits pagination behavior, performance implications (though fetchAll has a caution in schema), and whether the operation is read-only. The date header adds context but not behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The main description is a single sentence, which is concise and front-loads the purpose. However, it could be better organized (e.g., bullet points for filter types) to improve scanability. The date header is an external note, not part of the core description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 15 parameters and no output schema, the description is incomplete. It does not explain the return format, pagination defaults (size=20), or how to handle large result sets (fetchAll note is in schema but not description). The tool's complexity requires more context for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 67%, so many parameters have descriptions. The tool's description adds minimal value beyond the schema: it lists filter categories but doesn't explain parameter relationships (e.g., how searchType interacts with keyword). Baseline 3 is appropriate as schema does moderate work.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it queries a list of meeting minutes (会议纪要列表) and lists types (业绩会, 路演, 专家访谈, 调研纪要), making the resource specific. However, it does not explicitly differentiate from sibling tools like gangtise_roadshow_list or gangtise_research_list, which also deal with meetings or reports.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. The description does not indicate when to use this tool versus other list tools (e.g., gangtise_announcement_list, gangtise_research_list), nor does it specify prerequisite conditions or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 the tool queries cash flow statements, without mentioning read-only nature, data freshness, rate limits, or permissions. Essential behavioral context is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, but it includes redundant date context instructions (bracketed text) that are not strictly part of the tool's purpose. This verges on clutter, reducing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and 7 parameters, the description is too brief. It fails to explain how parameters interact (e.g., startDate vs fiscalYear) or what return data looks like. More detail is needed for complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the description adds limited value beyond the schema. It mentions filtering by period, fiscal year, and report type, but these are already documented. No additional semantic context is provided for parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool queries Hong Kong stock cash flow statements under Chinese accounting standards, with filtering options. The verb '查询' (query) and resource '港股现金流量表' (HK cash flow statement) are specific. It distinguishes from sibling tools like gangtise_cash_flow (A-shares) and gangtise_cash_flow_quarterly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as gangtise_cash_flow or gangtise_cash_flow_quarterly. The description lacks explicit context for selection or exclusions, relying solely on the tool name for differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 states supported formats but does not mention side effects, authentication requirements, rate limits, or what happens if the reportId is invalid. The tool likely performs a read operation, but this is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The functional description is a single sentence listing formats, but it is prefixed by a date/time bracket note that is not directly related to tool behavior. This adds noise and reduces conciseness. The structure could be cleaner without the prefix.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks information about the return format (e.g., binary data, URL, or file content) and authentication needs. With no output schema and many sibling tools, the description is incomplete for an AI agent to fully understand how to handle the tool's output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with both parameters already described in the schema. The description adds no new meaning beyond that, as it restates the fileType options already covered. Baseline score of 3 is appropriate since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool downloads foreign research reports and lists supported formats (PDF, Markdown, Chinese PDF, Chinese Markdown). It distinguishes from the list tool (gangtise_foreign_report_list) but does not explicitly differentiate from other download tools like gangtise_research_download. The verb 'download' and resource 'foreign research reports' are specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies that the tool is used after obtaining a reportId from gangtise_foreign_report_list, but it does not provide explicit guidance on when to use vs not use this tool, nor does it mention alternatives or prerequisites beyond the reportId. Usage context is clear but not comprehensive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should fully disclose behavior. It only states the action (download) but does not mention whether it is read-only, what is returned (file content, URL, etc.), permissions needed, or any limitations. The date prefix in the description is unrelated and may be confusing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The core description is very short (one sentence), which is concise, but it includes an extraneous date note that does not belong to the tool's purpose, reducing structural clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain what the download returns. It does not address return format, error handling, or required steps (e.g., prerequisite call to gangtise_knowledge_batch). The description is too minimal to fully guide an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the schema's description already notes that resourceId comes from gangtise_knowledge_batch. The tool description adds no additional parameter meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states '下载知识库资源文件' (download knowledge base resource file), which specifies a clear verb and resource. It distinguishes from sibling download tools like gangtise_announcement_download or gangtise_drive_download by indicating the resource type as knowledge base.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 other download tools in the sibling list. No context about prerequisites, conditions, or when to prefer this tool is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It does not disclose whether the tool is read-only, what data sources it uses, if it requires special permissions, or any rate limits. The only behavioral context is that it queries data; no safety or side-effect information is given.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is brief but includes a lengthy date-context instruction that is not part of the tool's purpose. The core description is one sentence, which is concise, but the extra preamble makes it less structured and less focused on the tool itself.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 7 parameters, no output schema, and returns potentially complex data (valuation time series with percentiles), the description does not explain return values, column names, or how to interpret results. This leaves significant gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds no additional meaning beyond the schema; it merely repeats the indicator options. The schema descriptions themselves are minimal (just enums), so the tool description does not improve understanding of parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries valuation indicators and historical percentiles, listing specific supported indicators (PE, PB, PEG, PS, PCF, EM). The verb '查询' and resource '估值指标及历史分位数' are specific and distinct from sibling tools that deal with financial statements or other data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 does not mention use cases, exclusions, or compare with sibling tools like financial statement queries or other valuation-related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 description merely states it queries data, without mentioning any side effects, permissions, rate limits, or data characteristics. For a data retrieval tool, this is insufficient transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence plus a date context note, which is concise and front-loaded. However, the date note is a meta-instruction that could be considered extraneous. Overall, it is efficiently structured without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 7 parameters and no output schema. The description provides a high-level summary but lacks details on the return format, pagination, or the meaning of 'cumulative' (year-to-date). For a complex financial data tool, this is incomplete guidance for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond what the schema already provides for each parameter. The description lists the supported filter types but does not elaborate on their values or usage beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states '查询A股现金流量表（累计口径）' (query A-share cash flow statement, cumulative basis), which is a specific verb and resource. The scope 'A股' distinguishes it from sibling tools like gangtise_cash_flow_hk (Hong Kong) and gangtise_cash_flow_quarterly (quarterly), making the purpose clear and distinct.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description only mentions supported filters (period, fiscal year, report type) but does not explain when to use this tool versus alternatives like gangtise_cash_flow_quarterly or gangtise_cash_flow_hk. No explicit guidance on when not to use or which context to prefer. The naming provides implicit hints, but not enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description should disclose behavioral traits. It omits whether the operation is read-only, expected output format, error handling, or performance implications. Only states the function without behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and front-loaded with a necessary date context note. No fluff, but could include more critical information without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 7 parameters, no output schema, and no annotations, the description is insufficient. It does not explain return data, field meanings, or query constraints. For a financial data tool, key details like typical cash flow items are missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds no parameter-specific meaning beyond the schema definitions. All parameters are well-documented in the schema, and the description offers no extra context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries A-share single quarter cash flow statements, using specific verb '查询' and resource 'A股单季现金流量表'. It distinguishes from siblings like gangtise_cash_flow (likely annual) and gangtise_cash_flow_hk (HK stocks) by specifying 'A股' and '单季'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like gangtise_cash_flow or gangtise_cash_flow_hk. The description lacks context on prerequisites, limitations, or preferred use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description fully shoulders transparency. It discloses the semantic search capability and batch limit but omits behavioral traits such as authentication requirements, rate limits, response format, or any side effects. The agent cannot infer safety or cost implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, containing two parts: a date context bracket note and a single-sentence core description. The date note is necessary for accurate temporal interpretation but adds length. Overall efficient, though the note could be separated or shortened.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite full schema coverage for inputs, the description lacks information about output format, return values, or pagination. With no output schema, the agent is left uninformed about what the search results contain. The tool is moderately complex (batch search, multiple resource types), yet behavioral context is incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All 4 parameters have descriptions in the schema (100% coverage), so the description adds limited value. It reiterates the max query count (already in schema as maxItems:5) and provides a date context note not directly tied to parameters. Baseline 3 is appropriate as schema already documents parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs semantic search in the Gangtise knowledge base (including reports, meeting minutes, opinions, announcements) and supports up to 5 query words per batch. It distinguishes from sibling tools by specifying batch semantic search, unlike other tools that target specific resource types or downloads.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a date context note for relative time references and a max query limit, but it does not give explicit guidance on when to use this tool versus alternatives like gangtise_knowledge_resource_download or other search tools. No when-not-to-use or alternative recommendations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must cover behavioral traits. It only mentions the current date context and filtering capabilities, omitting details on pagination (size/fetchAll), data freshness, permissions, or rate limits. This is insufficient disclosure for a 15-param tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence (plus date note) that is efficient and front-loaded. It avoids unnecessary words, though the brevity sacrifices detail for some parameters.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 15 parameters, no output schema, and no annotations, the description is too sparse. It does not explain robustly how the tool handles pagination (size/fetchAll), the meaning of objectList or permission, or result format. The date note partially addresses the time parameter context but overall completeness is low.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With only 33% schema description coverage, the description adds value by listing some filter categories (researchAreaList, institutionList, etc.) and providing a date/time context note. However, it fails to explain opaque parameters like from, objectList, permission, and brokerTypeList, leaving gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool queries roadshow schedules and lists multiple filter criteria (e.g., research area, institution, security). This clear verb+resource definition makes the purpose obvious, though it does not differentiate from sibling tools like gangtise_announcement_list.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for filtering roadshow schedules but provides no guidance on when to use this tool versus alternatives. No explicit when-not-to-use or prerequisites are mentioned, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose behavioral traits like read-only nature, authorization needs, or rate limits. However, it only states the query action without any behavioral information. It does not indicate whether the tool is safe or destructive, nor does it explain any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and to the point, consisting of one sentence after a date context note. The date context, while necessary for the system, is not directly part of the tool's purpose but is placed in the description. Overall, it is concise with no wasted words, though the date prefix could be separated.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no output schema, the description should explain what the tool returns. It only says 'query' without mentioning the result format, data structure, or typical response. For a tool with 6 parameters and multiple optional filters, the description lacks completeness about the output and usage scenario.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, so the schema already documents all parameters. The description adds little new meaning beyond echoing the holderType options. It does not clarify the relationship between parameters or provide additional context beyond the schema definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states '查询前十大股东或前十大流通股东', which specifies the verb (query) and resource (top ten shareholders or top ten tradable shareholders). It directly indicates what the tool does and distinguishes from the many sibling tools that deal with financial data but not specifically top holders.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus alternatives. It lacks context such as prerequisites, use cases, or when not to use it. The only hint is the '必填' comment in the parameter description, but no explicit usage guidelines.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must fully disclose behavioral traits. It only states the basic operation (status check) but omits details like read-only nature, error handling for invalid dataId, rate limits, or expected response structure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single short sentence, efficient and front-loaded. However, it could include a bit more context without harming conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
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 only one param, the description does not cover expected return values, possible statuses, or error conditions. It is incomplete for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% (no param descriptions in schema). The description adds that dataId is used to query status, but provides no format, source, or example. For a single required parameter, this is minimal additional meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks the generation status of an earnings review task by dataId. It uses a specific verb ('查询') and resource ('业绩点评任务的生成状态'), and distinguishes from sibling gangtise_earnings_review which likely creates/submits tasks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit usage guidelines or when-not-to-use instructions are provided. The context implies usage after obtaining a dataId from a task submission, but this is not stated. Sibling names hint at alternatives, but no direct guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description should disclose behavioral traits. It only states 'query' without mentioning read-only nature, data source, rate limits, or any side effects. The description fails to add value beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with a necessary date context note. It is concise and front-loaded, but the date note could be integrated more smoothly. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 7 parameters, no output schema, and no annotations, the description should offer more context (e.g., available fieldList options, output format). It is minimally complete but leaves gaps for a parameter-rich tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with all 7 parameters described in the input schema. The tool description does not add additional semantic meaning beyond what the schema provides. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states '查询A股单季利润表' (query A-share quarterly income statement), clearly identifying the tool's verb (query), resource (income statement), and scope (A-share, quarterly). It distinguishes itself from siblings like gangtise_income_statement (likely annual) and gangtise_cash_flow_quarterly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives like gangtise_income_statement (annual) or for HK stocks. The date context note is about dynamic date handling, not usage context. There are no explicit 'when to use' or 'when not to use' instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 the purpose and does not disclose any behavioral traits such as whether it is read-only, required permissions, rate limits, or data freshness. This is minimal transparency for a tool with zero annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The core description is a single sentence, but it is preceded by a long date context bracket that is extraneous and could be misleading. While the overall length is short, the inclusion of unnecessary information reduces conciseness. The structure is front-loaded with irrelevant context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there is no output schema and no annotations, the description should provide more context about the output format or structure. It does not describe what the extracted management discussion looks like, which leaves a significant gap for an agent to understand the return value.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for all three parameters, so the baseline is 3. The tool description does not add additional meaning beyond what is already in the schema. The parameter descriptions are adequate but not enhanced by the tool description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool extracts AI-collated management discussion from earnings call meeting minutes. The verb 'extract' and resource 'earnings call meeting minutes' are specific, and the tool name includes 'discuss_earnings_call', which distinguishes it from sibling tools like gangtise_management_discuss_announcement.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly suggests using this tool for earnings call analysis, but does not explicitly state when to use it, when not to, or mention alternative tools. The date context bracket provides contextual but not usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states the return type ('text or file path'), lacking disclosure of behavioral traits such as authentication needs, rate limits, or side effects beyond what is implied by 'download'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short but includes an extraneous date note that is unrelated to the tool's function. The core sentence is clear but could be restructured to separate context from semantics.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema is provided, and the description only vaguely mentions returning text or file path. It lacks detail on handling responses, error states, or file size limits, which are important for a download tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with brief descriptions for both parameters. The description adds little beyond the schema, meeting the baseline expectation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'download' and resource 'meeting minutes files' (会议纪要文件), and specifies the input 'summaryId'. It distinguishes from sibling tools like gangtise_summary_list and other download tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage after listing summaries, but provides no explicit guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist; description only mentions filtering capabilities. It does not disclose read-only nature, authentication needs, rate limits, or output format, leaving behavioral traits ambiguous.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is one sentence with a relevant, albeit meta, date context prefix. It is concise but could separate tool behavior from system instructions.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema provided, and description does not explain return values. For a data retrieval tool with 7 parameters, this is a significant gap in completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed descriptions. The description adds no extra meaning beyond schema, e.g., parameter dependencies or defaults. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description explicitly states it queries A-share balance sheet and supports filtering by period, fiscal year, and report type. The sibling tool 'gangtise_balance_sheet_hk' confirms distinction by market, making purpose specific and clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implicitly limits usage to A-share balance sheets but does not explicitly state when to use vs alternatives (e.g., HK, US). No when-not-to or prerequisite guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the waiting behavior and timeout, but does not clarify if the tool is read-only or destructive, nor does it address permissions or state changes. Basic info is present but insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two clear sentences, front-loaded with the primary purpose. No unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the basic function and timeout, but lacks details about return values on success, error handling, and the relationship with the check tool. Adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description does not add meaning beyond what the schema already provides for each parameter. The baseline of 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates an AI performance review report for a given stock and period. It implicitly differentiates from the sibling 'gangtise_earnings_review_check' which likely checks the result, making the purpose of submission clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 the check tool or explain when to use this submission tool vs. checking results.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. It mentions filters but does not disclose pagination behavior, rate limits, or result size constraints. The existence of 'size' and 'fetchAll' parameters hints at pagination, but description does not explain performance implications or defaults.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with a date hint is efficient and front-loaded. However, the date hint is placed at the beginning and could be seen as meta-instruction rather than tool behavior; it would be better placed in a separate note. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 18 parameters, no output schema, and no annotations, the description is insufficient. It does not explain return value structure, how to interpret the list, or how pagination works. For a complex query tool, more detail on expected output and parameter semantics is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low (39%). Description lists filter categories (e.g., securities, region, industry, broker, rating) which adds some meaning beyond bare parameter names, but many parameters (e.g., llmTagList, ratingChangeList, minReportPages) remain unexplained. The regionList description notes values come from gangtise_lookup, but other lists lack similar guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb '查询' (query) and resource '外资机构研报列表' (foreign institution research report list), and lists multiple filter dimensions (证券、地区、行业等). It effectively distinguishes from sibling tools like gangtise_research_list (domestic) and gangtise_foreign_report_download (download).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies usage for listing foreign research reports but provides no explicit guidance on when to use this tool vs. alternatives (e.g., gangtise_foreign_opinion_list, gangtise_research_list). No when-not-to-use or contextual exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries full burden. It only mentions date conversion and filtering support, but fails to disclose any behavioral traits such as read-only nature, authorization needs, rate limits, or response format. This is insufficient for a data query tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with a necessary date context instruction. It is front-loaded and concise, containing no redundant information. The date instruction could be slightly more streamlined, but overall it is clear and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 7 parameters and no output schema or annotations, the description is too brief. It does not explain return values, default behaviors, or how to combine filters. Compared to similar tools, more context (e.g., available fields, data ordering) is needed for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents all parameters. The description adds that the tool supports filtering by period, fiscal year, and report type, but this merely reiterates the schema descriptions without additional context or constraints. Baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries the Hong Kong stock income statement under Chinese accounting standards using specific verbs ('查询') and resources ('港股利润表'). This differentiates it from sibling tools like 'gangtise_income_statement' (likely A-share) and other HK financial statement tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for HK income statement data but does not explicitly state when to use this tool versus alternatives (e.g., other financial statements). No comparison or exclusions are provided, leaving the agent to infer context from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full transparency burden. It discloses no behavioral traits (e.g., read-only, auth needs, side effects). The minimal description offers only purpose, lacking operational details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with purpose, plus a date note. It is front-loaded and efficient, though the date context could be integrated or moved to a separate field.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 6 parameters, 2 required, no output schema, and no detailed operational guidance, the description is insufficient. It lacks explanation of return values, usage of optional parameters (periodList, fieldList), and breakdown behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so parameters are documented. The description adds a date context reminder but does not significantly enhance understanding beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: query main business composition by product, industry, or region. It specifies the verb (查询) and resource (主营业务), distinguishing it from sibling financial statement tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for main business breakdown but does not provide explicit guidance on when to use this tool versus alternatives (e.g., income statement). No exclusions or contextual cues are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states what the tool does (extract content) without disclosing traits like read-only nature, auth requirements, rate limits, or behavior when data is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is short and front-loaded with a necessary date reminder. Every sentence serves a purpose, though the date instructions could be seen as slightly verbose. Overall efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema is provided, and the description does not explain the return format or any side effects. For a data extraction tool, more detail on what the AI-organized content looks like would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with each parameter described in the input schema. The description adds no extra meaning beyond the schema; it merely restates the report type restriction already implied by reportDate. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool extracts AI-organized management discussion from financial reports (semi-annual/annual), with a specific date context. It distinguishes from sibling tool 'gangtise_management_discuss_earnings_call', which is for earnings call transcripts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies usage (for semi-annual/annual reports) but does not explicitly state when to use this tool vs alternatives like 'gangtise_management_discuss_earnings_call'. No exclusion criteria or when-not-to-use guidance provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 output format but does not disclose any behavioral traits such as being read-only, permissions needed, or rate limits. For a download tool, additional transparency about side effects or limitations would be expected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence but includes a date hint that is not directly relevant to the tool's function. The hint adds overhead and could be placed elsewhere. The purpose is stated clearly, but the structure could be cleaner.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description explains the output (Markdown text or PDF file path) but lacks specifics about the Markdown structure or PDF path format. With no output schema, more detail would improve completeness, but the description is adequate given the straightforward nature of the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds context by linking reportId to gangtise_research_list and clarifying fileType values (1=PDF, 2=Markdown), but this information is already present in the schema's parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'download', the resource 'brokerage research reports', and the output 'Markdown text or PDF file path'. It distinguishes from sibling tools like gangtise_research_list (lists reports) and gangtise_research_outline (likely provides outlines).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions that the reportId comes from gangtise_research_list, which implies a prerequisite but does not provide explicit when-to-use or when-not-to-use guidance. No alternatives are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavioral traits. It only mentions the tool returns Markdown content and that the input supports A-share codes (from schema). There is no information about potential limitations (e.g., rate limits, data freshness, AI generation quality, or failure conditions), leaving significant gaps for an agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that conveys the core action, input, and output format without any superfluous words. Every token contributes value, making it highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one required parameter, no output schema), the description provides the essential information. However, compared to the rich set of sibling tools (e.g., gangtise_one_pager, gangtise_summary_list), it lacks context on how the outline relates to other research outputs (e.g., length, level of detail) and any potential restrictions beyond A-share support.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description for the single parameter 'securityCode' already specifies '仅支持 A 股证券代码' (only supports A-share stock codes). The tool description does not add further meaning beyond this, so it meets the baseline expectation for a well-covered schema without adding extra semantic depth.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves an AI-generated research outline for a given security and returns Markdown content. It uses specific verbs ('获取'/'get') and a distinct resource ('AI生成公司研究提纲'/'AI-generated company research outline'), effectively differentiating it from sibling tools like gangtise_research_download (full reports) or gangtise_research_list (list of reports).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 such as gangtise_research_download or gangtise_investment_logic. An agent receives no hints about typical use cases, prerequisites, or exclusion criteria, leaving the decision entirely to inference from the purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 does not disclose pagination behavior, authentication requirements, or what happens if no groups are available. For a list tool, more transparency is expected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that directly states the tool's function. The date prefix adds context but is not part of the tool description; overall it is concise with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema is provided, so the description should clarify the return format. It only says 'list of IDs and names' but omits structure, pagination details (despite 'from' and 'size' parameters), and any filtering behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 67% (two of three parameters have descriptions). The description does not add any parameter-specific guidance beyond the schema, such as how 'roomName' works as an array. It meets the baseline for moderate coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries a list of available WeChat group IDs and names, using a specific verb ('查询') and resource ('微信群 ID 和群名称列表'). It implicitly distinguishes from sibling tool gangtise_wechat_message_list which deals with messages.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. It is implied that this tool is a prerequisite for obtaining group IDs to use with gangtise_wechat_message_list, but no when-not or exclusion criteria are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits beyond basic filtering. It mentions date handling but does not cover pagination, response format, or potential side effects. The fetchAll parameter hints at pagination but is not explained in the description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, with one sentence of functionality plus a date context bracket. It is front-loaded with the date instruction, which is useful. No unnecessary words, but could be slightly more structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 11 parameters and no output schema, the description is too brief. It does not explain return values, pagination behavior, or how to interpret results. For a list endpoint, more context is needed to ensure correct usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 73%, so the schema already describes most parameters. The description adds a general list of filter types but does not provide additional meaning beyond what is in the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb '查询' (query) and the resource '微信群消息列表' (WeChat group message list), and distinguishes from sibling 'gangtise_wechat_chatroom_list' by focusing on messages rather than groups.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a date context instruction but does not provide explicit usage guidelines, such as when to use this tool vs alternatives or prerequisites. It is implied that it's for listing messages, but no exclusions or when-not-to-use advice is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states basic query and filter capabilities, failing to disclose pagination behavior (though schema has size/fetchAll), result format, or any side effects. The date context note is about query interpretation, not tool behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with a necessary date context note, no redundancy, and front-loaded key information. Every element serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 10 parameters and no output schema, the description is insufficient. It omits details on pagination, keyword search behavior, search type differences, and expected output. A more complete description would explain how the tool works, e.g., 'returns a paginated list of announcements matching filters'.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 60%; the description adds context by listing three filter types (security, category, time) matching parameters. However, it does not explain keyword, searchType, rankType, from, size, or fetchAll beyond what's in schema. The date note in startTime/endTime schema helps but is not from the description itself.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries Hong Kong stock announcement lists with filtering by security, category, and time range, distinguishing it from siblings like gangtise_announcement_list (likely A-shares) and gangtise_announcement_hk_download (download).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for listing HK announcements with filters but does not explicitly state when to use alternatives or when not to use this tool. No exclusion criteria or alternative references are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 behavioral traits. The description mentions the tool is AI-generated and supports briefing versions, but it does not indicate whether the operation is read-only or has side effects, nor does it address pagination, performance (fetchAll is a param but not explained), or data freshness. The description lacks sufficient behavioral transparency for an autonomous agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences: a date context instruction followed by the core function. The structure is logical, placing context first. However, the date instruction is lengthy and could be streamlined or moved to parameter descriptions. No unnecessary words, but the date block slightly distracts from the main purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 8 parameters, no output schema, and moderate complexity. The description covers the basic purpose and briefing versions but does not describe the output format (e.g., fields in each briefing item, like title, summary, date). The date context handling is a plus, but without output schema or return value hints, the description is not fully complete for an agent to understand the tool's full behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 63%, with some parameters like categoryList and startDate having descriptions. The description lists briefing versions (早报, 午报, etc.) which correspond to categoryList enum values, adding slight contextual meaning. However, for parameters like withRelatedSecurities and withCloseReading, neither the schema nor the description explains their purpose. The description does not significantly enhance understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries AI-generated hot topic briefing lists and supports multiple versions like morning, noon, afternoon flash, and evening. The verb '查询' (query) and resource '热点话题简报列表' are specific, and the name 'gangtise_hot_topic' aligns well. Among many sibling tools focused on different data types (announcements, financials, research), this one is distinctively for hot topic briefings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a date context instruction ('当前日期 2026-05-27...') that guides how to interpret relative dates. However, it does not explicitly state when to use this tool versus alternatives (e.g., gangtise_research_list or gangtise_summary_list), nor does it mention any prerequisites or exclusions. The date handling is useful but incomplete as a usage guideline.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and description only states it returns HTML content. Lacks disclosure of read-only nature, authentication requirements, rate limits, or side effects. For a download tool, minimal behavioral context beyond the action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is short and to the point, with a necessary date-reminder prefix. Avoids fluff, though the date note is meta-context rather than tool description. Efficient overall.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers basic purpose and output format but lacks detail on what constitutes an independent opinion, how it differs from other downloads, any limitations, or expected HTML structure. Adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters described. The description adds no new information beyond the schema, only referencing the language option already defined. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (download) and resource (independent researcher opinion file), specifying output as HTML content with language options. Differentiates from sibling download tools like foreign_report_download and research_download by the specific resource type.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies that opinionId should be obtained from gangtise_independent_opinion_list, but does not provide explicit guidance on when to use this tool versus alternatives or any prerequisites/exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description gives no behavioral details beyond the basic query function. It does not mention data freshness, rate limits, or any side effects, leaving the agent uninformed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the core purpose. No unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite being a simple tool, the description lacks context such as return format, typical use cases, or integration with other tools. It does not compensate for missing annotations or output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds no extra meaning beyond the parameter descriptions already in the schema. Baseline score is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries index daily K-line data for Shanghai, Shenzhen, and Beijing indices. It is distinct from sibling tools like gangtise_day_kline (stocks) and gangtise_day_kline_hk (Hong Kong).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies it is for index data but does not explicitly state when to use this over other kline tools or any alternatives. No when-not guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the tool is local and returns data directly without API calls, which are useful behavioral traits. It could add more about data freshness or limitations, but core behavior is communicated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of two clear, front-loaded sentences that define the tool's purpose and list available categories. No redundant words; every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
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 a straightforward purpose (lookup reference data), the description covers its functionality adequately. It explains the data types and the local nature, though it could mention that this data is often used to populate parameters in other tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one parameter with enum values and descriptions, achieving 100% coverage. The tool description lists the same categories, reinforcing but not adding significant new meaning beyond the schema. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries local static reference data and lists eight specific categories (research areas, broker organizations, etc.). It effectively distinguishes from sibling tools that focus on specific data types like announcements or financial statements.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions 'no need to call API, directly return local data,' implying it is a lightweight, fast lookup. However, it does not explicitly state when to use this tool over siblings or when not to use it, leaving the agent to infer the context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the basic query action but fails to disclose any behavioral traits such as authentication needs, rate limits, or data scope (e.g., only A-shares).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no redundant information. It effectively communicates the core purpose with minimal words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite its simplicity, the description lacks crucial context such as return format, typical fields, or ordering of results. It is insufficient for an agent to fully understand the tool's behavior without additional inference.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 80%, and the description only restates the required parameter without adding new meaning. The description does not elaborate on optional parameters like field or limit, making it merely adequate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries minute-level K-line data for A-shares, specifying the resource and action. It distinguishes from sibling tools like gangtise_day_kline by explicitly mentioning minute-level and A-shares.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by requiring a single security code, but does not provide explicit guidance on when to use this tool over alternatives like gangtise_day_kline or gangtise_day_kline_hk. No when-to-use or when-not-to-use context is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It adds a date-handling instruction for current date/time, which is useful. However, it does not disclose pagination behavior, rate limits, authentication needs, or whether results are read-only. The mutation risk is not clarified, but the tool name 'list' implies 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with a date instruction prefix. It is reasonably concise, though the date note could be moved to a separate instruction or annotation. Every sentence serves a purpose, but the structure could be improved by separating context from the main purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 15 parameters, no output schema, and no annotations, the description covers the purpose and filter capabilities but lacks details about output format, pagination defaults, or performance implications of fetchAll. The schema partially addresses size and fetchAll, but the description does not integrate this explicitly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 80%, so baseline is 3. The description does not add parameter details beyond the schema; the date note is already present in the schema's startTime/endTime descriptions. No additional semantic value is provided by the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it queries a list of domestic institutional chief analyst opinions with filters, matching the tool name. It does not explicitly distinguish from sibling tools like gangtise_foreign_opinion_list, but the name and context imply differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description lists supported filters but provides no guidance on when to use this tool versus alternatives (e.g., foreign or independent opinion lists). Usage context is implied by the tool name and sibling names, but no explicit when-not-to-use or alternatives are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavioral traits. It mentions the output format (Markdown), which adds some context, but does not address side effects, authentication needs, rate limits, or any other behavioral characteristics. The description 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence, front-loaded with the main action and result. Every word contributes meaning; there is no redundancy or unnecessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema, no annotations), the description is reasonably complete. It explains the purpose and output format. However, it could hint at the report's structure or content to fully compensate for missing output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents the securityCode parameter. The description mentions '指定证券' (specified security) but adds no extra parameter insight beyond what the schema provides. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool generates a peer competition comparison report for a specified security, using specific verbs (生成) and resource (AI 同业竞争格局对比报告). It distinguishes itself from sibling tools like gangtise_one_pager or gangtise_research_outline by specifying the exact type of report.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
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 specify prerequisites, suitable scenarios, or when not to use it. This lack of usage direction reduces its helpfulness for an AI agent deciding among many report tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description lacks behavioral details such as read-only nature, pagination behavior, or performance implications. The description mentions filtering but does not explain how results are returned or limited. This is insufficient for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise, consisting of a context note and a single sentence defining the tool's function. Every word is necessary, and there is no redundancy. It is appropriately front-loaded with the date context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 8 parameters, no output schema, and no annotations, the description is somewhat incomplete. It explains the core functionality but leaves out details on pagination, defaults, and response format. The schema covers many parameters, but the description could provide more behavioral context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaning by listing the filtering dimensions (keyword, category, time range), which map to schema parameters. However, it does not cover all parameters (e.g., 'from' and 'spaceTypeList' are not mentioned). Schema already describes 75% of parameters, so the description provides moderate additional value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: querying a list of voice recording transcriptions. It matches the tool name and specifies filtering options. However, it does not explicitly distinguish from sibling list tools like gangtise_drive_list, but the resource type (records) is distinct enough.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates when to use the tool (to list recordings) but does not provide guidance on when not to use it or alternatives. No explicit exclusionary language is present, leaving the agent to infer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 the query function and a date conversion rule, failing to mention important aspects like read-only nature, required permissions, rate limits, or the structure of the response. The description adds minimal behavioral context beyond the parameter schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two lines: the first sets date context, the second defines the purpose. It is concise, front-loaded, and contains no redundant or irrelevant information. Every sentence serves a clear function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters (including an array type) and no output schema, the description lacks details on the return format, how to use the consensusList array (e.g., selecting multiple metrics), and pagination or limitations. It adequately covers the date interpretation context but is incomplete for an agent to fully understand usage without additional inference.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description's mention of EPS, PE, etc. aligns with the consensusList options described in the schema, but does not add significant new meaning. The date conversion rule is already present in the schema descriptions for startDate and endDate. Overall, the description adds marginal value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it queries earnings forecast consensus expectations, listing specific metrics (EPS, PE, net profit, ROE). This clearly distinguishes it from sibling tools like gangtise_income_statement or gangtise_balance_sheet, which serve different financial data purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a date interpretation note but does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites or exclusions. The usage is implied by the purpose, but no direct comparative guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
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 does not mention that the operation is read-only, safe, or any potential side effects. The description merely restates the schema, missing transparency on authentication or limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description includes an unnecessary date context prefix that is not relevant to the tool's purpose. The core sentence is concise, but the extraneous note reduces efficiency.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the tool's function and main parameters, but lacks information about the output format (e.g., file download, raw data). Without an output schema, the description should hint at what the agent receives.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds value by explaining the options for contentType ('可选原始音频、ASR文字或AI摘要') and implying that recordId comes from the list tool. This goes beyond the schema's concise descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('下载') and the resource ('语音录音转写内容'), with specific options (原始音频、ASR文字、AI摘要). It distinguishes from sibling download tools (e.g., gangtise_announcement_download) by targeting record content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives. The schema indicates recordId comes from gangtise_record_list, which implies a prerequisite, but the description does not state it. Context is adequate but lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses the return type (matching securities and GTS codes) but lacks details on rate limits, pagination, or any destructive behavior (none expected). The description is minimal for 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core action ('按关键词搜索证券'), and efficiently covers the key supported features. No waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, and the description only vaguely states '返回匹配证券及其 GTS 代码'. Missing details on response structure (fields, pagination), but given the tool's simplicity, it is marginally adequate. Sibling tools with similar descriptions indicate this is typical.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description largely repeats the schema descriptions (e.g., keyword accepts name/code/pinyin, category filters, top limits results). It adds no additional meaning beyond what the schema already provides, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for securities by keyword, supports multiple formats (Chinese name, code, pinyin, English), and returns matching securities with GTS codes. This is specific and distinguishes from sibling tools like gangtise_lookup or gangtise_edb_search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for searching securities, but does not explicitly state when to use this tool over alternatives (e.g., gangtise_lookup for exact matches, gangtise_edb_search for economic data). No when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description does not disclose pagination behavior, potential rate limits, or whether the tool is read-only. The date context note is helpful but does not cover behavioral traits beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with a front-loaded date context note. It is efficient and avoids verbose repetition, though it could be slightly more structured (e.g., listing filters explicitly).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 15 parameters and no output schema, the description gives only a high-level overview. It does not cover many parameters or explain the return format, pagination, or behavior when filters are empty. This is insufficient for a tool with such complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is low (33%). The description lists filter types (研究方向, 机构, etc.) corresponding to array parameters, which adds some meaning. However, many parameters (from, keyword, size, fetchAll) are not explained in the description, so it only partially compensates for the schema gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries a list of research visit schedules (调研日程列表) and lists multiple filter dimensions. This distinguishes it from sibling tools that handle financial statements, downloads, or other data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for filtered queries of site visits but provides no explicit guidance on when to use this tool versus alternatives, no when-not-to-use scenarios, and no prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states the tool's purpose and filtering options. It does not disclose behavioral traits such as pagination, rate limits, side effects, or response format. For a query 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences. The first provides essential context for relative date handling, and the second states the core purpose. No wasted words; front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 11 parameters, no output schema, and no annotations, the description covers the basic purpose and filtering dimensions but lacks details on return structure, pagination, or parameter relationships. Adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 64%, so the schema already documents most parameters. The description does not add new semantics beyond listing filter dimensions (security, type, category, time range). Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states '查询 A 股公告列表' (query A-share announcement list) and lists filtering capabilities by security, announcement type, category, and time range. It distinguishes from sibling tools like gangtise_announcement_hk_list (HK stocks) and gangtise_announcement_download (download).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for A-share announcements via the term 'A股', and sibling names reinforce this distinction. However, it lacks explicit when-to-use/not-use guidance or alternatives, but the context is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only lists filter options. It does not disclose behavioral traits such as whether it is read-only, potential rate limits, or data freshness. The tool name suggests a query, but the description adds minimal beyond that.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is highly concise with two sentences: one for date context and one for purpose. Every word is purposeful, and no unnecessary information is included.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 7 parameters (1 required), no output schema, and many siblings, the description adequately covers the main filtering options but omits mention of fieldList and does not guide selection among siblings. The date context instruction is useful but not about tool behavior. Overall, it is minimally complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed descriptions for each parameter. The description adds a summary of filter types ('期间、财年、报告类型筛选'), but does not provide additional meaning beyond what the schema already offers. Score is baseline 3 for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it queries Hong Kong balance sheets under Chinese accounting standards, with specific filter options (period, fiscal year, report type). This distinguishes it from siblings like gangtise_balance_sheet (likely A-share) and other HK financial tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies it is for HK stocks under Chinese accounting standards, but does not explicitly state when to use vs alternatives or when not to use. No sibling names are mentioned for comparison, but the scope is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
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 discloses the default behavior (returns all pools' stocks if parameter omitted), which is useful. However, it does not mention whether the tool is read-only, requires authentication, has rate limits, or any side effects. With no annotations, more behavioral context would be expected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (one sentence plus a system date note) and directly states the tool's purpose. The date context prefixed is somewhat extraneous for the tool itself, but the core message is clear and efficiently delivered.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (1 optional parameter, no required fields, no output schema), the description is adequately complete: it specifies the action, the resource, and the default behavior. It does not explain return values, but that is acceptable because there is no output schema to supplement.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema coverage is 100% (only one parameter, poolIdList, with a detailed schema description including default). The description restates the default behavior but adds no new semantic information beyond what the schema already provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states '查询指定自选股池中的证券列表' (query securities list in specified watchlist pool), which identifies a specific verb (查询/query), resource (自选股池中的证券列表/securities in stock pool), and distinguishes from sibling gangtise_stock_pool_list (which lists pools, not stocks).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains default behavior when poolIdList is omitted ('不传 poolIdList 时默认返回所有池的股票'), implying when to use the parameter. However, it does not provide explicit guidance on when to use this tool versus alternatives or when not to use it, leaving the agent to infer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
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 adds context (daily report, morning/night edition, date constraint) but does not describe return format, pagination, or other behavioral traits. The description adds some value beyond the schema but is 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with a date/timezone prefix. It is concise, front-loaded, and every part is necessary. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters, no output schema, and no annotations, the description provides the basic purpose and input requirements but lacks details about the report's content, return format, or potential errors. It is adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with each parameter having a description. The description adds minimal additional meaning beyond the schema (e.g., '早报或晚报版' mirrors the type parameter's enum values). Baseline 3 is appropriate since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action: '获取指定主题的每日跟踪报告（早报或晚报版）', specifying the resource (daily tracking report for a theme) and distinguishing it from sibling tools like gangtise_hot_topic or gangtise_investment_logic.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions required inputs ('需传入主题 ID 和日期') but does not provide explicit guidance on when to use this tool versus alternatives or when not to use it. The usage context is implied but lacks exclusions or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. States it downloads files, but lacks details on error handling, permissions, or side effects. Minimal but accurate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The core description is concise, but it is prefixed by a lengthy date processing instruction that is not specific to this tool, reducing efficiency. The main sentence is front-loaded but could be cleaner.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, and description fails to explain what the tool returns (e.g., file content, URL, format). Lacks information on file size, encoding, or behavior on failed download. For a download tool, this is a significant gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. Description adds value by clarifying that announcementId originates from gangtise_announcement_list, which aids understanding. fileType is adequately described in schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb (download), resource (A-share announcement file), and key parameter (announcementId). Distinguishes from sibling tools by specifying 'A股' (A-share), unlike Hong Kong variants.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly mentions that the announcementId comes from gangtise_announcement_list, providing a prerequisite. However, does not state when not to use it or explicit alternatives (e.g., Hong Kong counterpart).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions the output format (Markdown) but does not disclose any behavioral traits such as whether the operation is read-only, if it triggers a long computation, or any side effects. For a report generation tool, latency or API costs could be relevant but are omitted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, consisting of two short sentences that convey purpose and output format without unnecessary detail. Every word contributes value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (single input, Markdown output) and the absence of an output schema, the description is complete enough. It covers the essential purpose and output format. However, it could mention the type of investment logic (e.g., fundamental, technical) or any limitations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (one parameter 'securityCode' with description 'A-share or Hong Kong stock code'). The tool description does not add additional meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'generates an AI investment logic analysis report for a specified security and returns Markdown content.' The verb 'generate' and resource 'investment logic report for a security' are specific. It distinguishes from siblings like 'gangtise_balance_sheet' or 'gangtise_research_list' which deal with different data types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
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. It only states what it does, leaving the agent to infer from sibling names. There is no mention of prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It indicates the tool returns Markdown content, implying a read operation without side effects, but fails to disclose whether it caches data, requires authentication, or any other behavioral nuances. The description is minimally adequate but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence in Chinese that efficiently conveys the core purpose and output format. Every word is necessary, and the structure is front-loaded with the action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With one simple parameter and no output schema, the description provides sufficient context for the tool's role. It differentiates well among many siblings. Minor omission: it does not explicitly state the security types beyond what the parameter description says, but overall it is complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% because the single parameter 'securityCode' has a description in the schema ('A 股或港股证券代码'). The tool description adds no additional meaning beyond what the schema already provides, so baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates an AI one-page investment summary for a specified security and returns Markdown content. It uses a specific verb ('生成'/generate) and resource ('投资摘要'/investment summary), and the distinct output format differentiates it from siblings like financial reports or announcements.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for generating a concise investment summary but provides no explicit guidance on when to use it versus alternatives like research reports, foreign opinions, or other listing tools. No when-to-use or when-not-to-use cues are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only mentions what is returned but omits behavioral traits like auth needs, rate limits, or side effects. 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is a single sentence plus context note; highly concise and front-loaded with core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
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 covers purpose and return fields. Minor gap: no output schema, but return structure is hinted.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist; schema coverage is 100%. Description adds no parameter info but is sufficient given zero params. Baseline 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: query the user's stock pool list and return pool ID and name. It distinguishes from sibling tools like gangtise_stock_pool_stocks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use or alternatives, but the description implies usage for retrieving stock pool lists. Sibling tools provide context but are not mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It states the tool is historical only and hints at automatic sharding for 'all' security, but does not disclose rate limits, output format, or potential side effects. Given the absence of annotations, this is insufficient for agents to fully understand tool behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, consisting of two clear sentences with no redundancy. Every word serves a purpose, efficiently conveying key information without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
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, and moderate complexity. The description covers market scope, historical nature, and bulk data handling, but lacks details about the return format (e.g., typical fields like open, close). This is a notable gap given the absence of an output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds value by elaborating on the 'all' option for security with auto-sharding behavior and the role of startDate/endDate for full market pulls. This context goes beyond the schema's basic descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it queries A-share historical daily K-line data for Shanghai, Shenzhen, Beijing markets, and explicitly distinguishes from real-time data by referencing gangtise_realtime. It also explains the 'all' option for full market data with automatic sharding, making the purpose specific and differentiated from siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description advises using gangtise_realtime for intraday data, providing a clear alternative. However, it does not explicitly mention other market-specific siblings like gangtise_day_kline_hk or gangtise_day_kline_us, though their names imply usage for other markets. The guidance is good but could be more comprehensive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
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 correctly notes '仅历史' (historical only) and excludes real-time usage, which is the key behavioral trait. However, it does not disclose other behaviors such as read-only nature, data limits, rate limits, or response format. For a simple retrieval tool, this is adequate but not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single compact sentence with a parenthetical note, containing no redundant words. It is front-loaded with the core purpose, followed by the exclusion guidance. Every word contributes value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (historical K-line data), good schema descriptions, and common domain knowledge, the description is mostly complete. It could mention that it returns daily OHLC data, but the 'K line' term and field parameter imply that. Without an output schema, the description is sufficient for an agent to understand the tool's role among siblings.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description does not add any parameter-specific meaning beyond what the schema already provides. The schema descriptions for fields like security, startDate, endDate, limit, and field are self-explanatory. No additional context is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: querying historical daily K-line data for Hong Kong stocks. It distinguishes from other tools by specifying '港股' (HK stocks) and contrasts with real-time data via gangtise_realtime. The sibling tools include other day_kline variants for different markets, and this tool is uniquely identified by name and description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use (historical) and when not (real-time), and recommends an alternative (gangtise_realtime). However, it does not explicitly differentiate from other day_kline tools for different markets (e.g., gangtise_day_kline for A-shares), leaving some ambiguity. Still, the 'HK' in name and '港股' provide implicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description mentions batch size and date interpretation based on current date but does not explicitly state read-only nature or other behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with essential information, though the initial date reminder is slightly extraneous. Overall, no wasted sentences.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, and the description does not explain the return format or structure. For a data query tool, this omission reduces completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds context by linking indicatorIdList to gangtise_edb_search and clarifying date format with current date reference.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it queries time-series data for industry indicators by ID, with a batch limit of 10, and specifies the ID source from another tool. This distinguishes it from sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates that indicator IDs come from gangtise_edb_search, providing usage context. However, it does not explicitly state 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.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the behavioral transparency burden. It indicates a read-only search operation, but lacks details on authentication, rate limits, or result behavior (e.g., exact vs fuzzy matching). Given the simplicity of the search, the description is adequate but not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise with two main parts: a date context note in brackets (important for temporal references) and the core purpose. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple search tool with 2 parameters and no output schema, the description covers the essential purpose and output. It could mention the result format (e.g., list of objects) but is otherwise complete for an agent to use effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description does not add new meaning beyond the schema's parameter descriptions. It mentions searching by keyword but no extra semantics for parameters like `limit` (default 100, max 200). The baseline of 3 is appropriate as the schema already explains the parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (search by keyword), target (行业经济数据库指标列表), and output (指标ID和名称) for subsequent time series data queries. It distinguishes itself from the sibling tool `gangtise_edb_data` which would use the returned IDs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description hints at the tool's purpose as a precursor to time series data retrieval ('用于后续查询时序数据'), providing context for when to use it. However, it does not explicitly state when not to use it or mention alternatives among the many sibling tools, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description partially reveals behavior: it's read-only (query), only historical data, and automatic sharding when using 'all'. However, it lacks details on data source, freshness, rate limits, or confirmation that no destructive actions occur. A 3 is appropriate as it provides some but not rich context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences. The first sentence efficiently states the core purpose and directs to an alternative. The second adds an important usage note. Every word serves a purpose, and the key information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters, no output schema, and no annotations, the description covers essential aspects: purpose, alternative tool, and special parameter usage. It is understandable and actionable. However, it could be improved by briefly mentioning the expected output format (e.g., OHLCV fields) or common limitations, but overall it provides sufficient context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and all parameters have descriptions. The description adds value by explaining the 'all' magic value for security, the required pairing of security='all' with startDate/endDate, and the automatic sharding behavior. It also gives code format examples, enhancing understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the tool queries US stock historical daily K-line data for NYSE/NASDAQ/AMEX, with explicit code format examples (AAPL.O/.N/.A). It distinguishes itself from real-time data by referencing gangtise_realtime, and from other day_kline siblings by market focus (US vs HK vs A-shares).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states when to use (historical US daily data) and gives a direct alternative for real-time data (gangtise_realtime). It also explains the 'all' parameter usage for full market pulls. However, it does not explicitly mention when not to use or other alternatives among the many sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses asynchronous behavior, wait time parameter, and that timeout returns a dataId. This gives reasonable transparency into the tool's operation, though it doesn't cover rate limits 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is two sentences, no filler, and front-loaded with the core purpose. Every part earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the tool's purpose and async behavior adequately. However, without an output schema, more detail about what the report contains might be helpful, but not required for basic use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with parameter descriptions already present. The description mentions viewpoint and waitSeconds but adds no new meaning beyond what is in the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it generates an AI bull-bear debate report for a given investment viewpoint. It distinguishes itself from sibling tools like gangtise_viewpoint_debate_check by mentioning the async behavior (waitSeconds, dataId on timeout), which implies a submit-then-check pattern.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description explains the wait mechanism and default timeout, giving context on usage. However, it does not explicitly mention the alternative (gangtise_viewpoint_debate_check) for retrieving results after timeout, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that the tool only reads files with a specific prefix, in a temporary directory, generated by the same process. It also explains the chunked reading mechanism. It does not cover error scenarios or return format, but for a read-only utility, 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences long, front-loading the purpose and then adding usage conditions. Every sentence is necessary and clear. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers purpose, usage conditions, and basic constraints. However, it does not mention the return format or error handling. Given the tool's nature (reading truncated data), a hint about output structure would improve completeness. Still, it's fairly complete for a utility tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with good descriptions for all three parameters. The description adds value by explaining that 'saved_to' comes from other tools' '_saved_to' field, which clarifies its origin. Offset and limit are standard and their schema descriptions are sufficient.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: reading truncated large responses from other tools. It specifies the triggering condition (when truncated: true and _saved_to field present) and the method (chunked reads by offset/limit). This distinguishes it from sibling tools, which are all data-fetching tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use the tool: when other tools return truncated responses with a _saved_to path. It also restricts usage to files with the gangtise-mcp- prefix in the system temp directory. No alternatives are needed as no sibling tools serve this purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description explains return behavior: non-trading hours return last trading day snapshot, suspended stocks return last valid snapshot. Lacks details on auth or rate limits but sufficient for a query tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise, front-loaded with main purpose, followed by key details. No unnecessary words. Every sentence adds information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers main use cases and edge cases, distinguishes from siblings. No output schema but return format is standard for snapshots. Slightly incomplete on pagination or limits, but adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions. Description adds value by explaining default behavior ('默认不传 = 返回全量字段') and when to use field parameter, plus requirement to include identifier fields.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries real-time market snapshots covering A/HK/US stocks with mixed codes. It specifies behavior during non-trading hours and for suspended securities, and distinguishes from k-line interfaces.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use this tool vs. day-kline tools: '日 K 线接口不含盘中数据，问现在/此刻请走本工具.' Also covers edge cases like non-trading hours and suspended stocks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![gangtise-mcp MCP server](https://glama.ai/mcp/servers/gangtiser/gangtise-mcp/badges/card.svg)](https://glama.ai/mcp/servers/gangtiser/gangtise-mcp)

Score Badge

Copy to your README.md:

[![gangtise-mcp MCP server](https://glama.ai/mcp/servers/gangtiser/gangtise-mcp/badges/score.svg)](https://glama.ai/mcp/servers/gangtiser/gangtise-mcp)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gangtiser/gangtise-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server