agentladle/financial-reports

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

The description presents the tool as a read-only search, but annotations indicate destructiveHint=true. This contradiction is severe. The description does not disclose any side effects or authentication needs, but the contradiction alone warrants a score of 1 per rules.

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

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

The description is well-structured with sections (critical rules, parameters guide, examples) and front-loaded purpose. While lengthy, it is organized and every section adds value, though a bit verbose for a simple search tool.

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

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

Given no output schema and multiple parameters, the description covers usage scope (A-share annual reports), parameter restrictions, examples for different scenarios, and guidance on combining with sibling tools. It is sufficiently complete.

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

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

Despite 100% schema coverage, the description adds substantial value: conversion rules for keywords, matchMode usage scenarios, page range logic, and example parameter combinations. This goes well beyond the schema's basic descriptions.

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

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

The description clearly states it is a keyword-based full-text search tool for financial reports, distinguishing it from siblings like getFinancialReportPages or getReportChapters. The verb '检索' (search) and resource '财务报告全文' (full-text of financial 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.

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

The description provides explicit rules: forbid natural language sentences, convert user queries to keywords, use synonyms, restrict retrieval conditions (e.g., require reportType for cross-company searches), and suggests using ANY mode first. It also gives when-not-to use (e.g., avoid specifying stockCode without date filter) and alternatives like sibling tools.

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

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

The description describes a read-only operation (retrieving pages), but the annotations indicate destructiveHint=true, which contradicts the read-only nature. This contradiction violates the requirement for consistency, leading to a low score.

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

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

The description is well-structured with clearly labeled sections (critical_rules, function_description, etc.) and front-loads the core purpose. While somewhat lengthy, all sections contribute value, making it efficient for an agent.

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

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

The description covers purpose, constraints, parameters with examples, return format, and example calls. It lacks error handling details (e.g., out-of-range pages) but is otherwise complete for the tool's complexity.

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

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

The description adds examples and clarifications beyond the input schema, such as concrete stock code examples and explanation of the reportType format (4-digit year + 'a4'). Although schema coverage is 100%, the extra detail aids parameter understanding.

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

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

The description clearly states the tool's purpose: retrieving complete content of financial report pages by page number interval, with filtering by stock code and report type. This distinguishes it from sibling tools like 'financialKeywordSearch' (keyword search) and 'getReportChapters' (chapter retrieval).

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

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

The description provides explicit data range limitations via the critical_rules section, stating it only covers China A-share annual reports and excludes US/HK stocks and other report types. This gives clear context on when not to use the tool, though it does not directly compare with siblings.

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

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

Annotations include destructiveHint=true, suggesting potential side effects, but the description describes a read-only query operation without clarifying any destructive behavior. It does not add context beyond annotations regarding permissions, rate limits, or side effects, creating a gap in transparency.

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

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

The description is well-structured with clear sections (critical_rules, function_description, parameters_guide, examples). It is front-loaded with purpose, but some repetition exists (e.g., listing statements multiple times). Overall efficient for the complexity.

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

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

Given no output schema, the description provides examples showing return format. It covers scope, required params, optional param, and format details. Lacks error handling or reliability notes, but sufficient for a query tool.

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

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

With 100% schema coverage, baseline is 3. The description adds value by explaining reportType format, providing category examples, and including detailed examples that illustrate parameter usage, surpassing the schema's descriptions.

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

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

The description clearly states the tool's purpose: querying the start page numbers of four consolidated financial statements in annual reports. It specifies the resource (financial reports) and the action (get start pages), distinguishing it from sibling tools like getFinancialReportPages by focusing on specific statements.

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

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

The critical_rules section explicitly limits usage to Chinese A-share annual reports, excluding US, HK, and interim reports. This provides clear when-to-use and when-not-to-use guidance. While it does not name alternative tools, the scope definition helps users choose appropriately.

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

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

Description claims a read-only operation ('获取'), but annotations set destructiveHint=true and readOnlyHint=false, implying potential destructive behavior. This is a direct contradiction; no mention of side effects or destructive actions in description.

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

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

Description is well-structured with sections (critical rules, parameter guide, example). It is somewhat lengthy but each section adds necessary context. Front-loaded with purpose.

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

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

Provides clear output example showing chapter list with page numbers and count, compensating for lack of output schema. Covers data scope and parameter details well. Could mention error handling but overall complete.

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

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

Schema already describes both parameters (100% coverage). The description adds value by explaining stockCode format with example and reportType format with supported values (e.g., 2023a4, 2024a4), going beyond basic schema.

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

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

The description clearly states '获取财务报告的完整章节目录' (retrieve complete chapter table of contents of financial reports), specifying the verb and resource. It distinguishes from siblings like getFinancialReportPages and financialKeywordSearch which focus on different aspects.

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

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

The <critical_rules> section explicitly limits usage to China A-share annual reports, providing clear context. It does not compare directly with sibling tools or state when not to use, but the scope is well-defined.

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

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

Description indicates a read-only search, but annotations set destructiveHint=true, contradicting the behavior. No additional behavioral details provided beyond the annotation contradiction.

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

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

Description is well-structured with clear sections, no wasted words, and front-loaded purpose. Examples and return format enhance clarity efficiently.

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

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

Despite no output schema, description provides return format and example output. All parameters and constraints are documented, making it complete for a simple search tool.

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

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

Schema coverage is 100%. Description adds value by specifying fuzzy vs exact matching and default size, but these are also in schema. Meeting baseline for high coverage.

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

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

The description clearly states the tool queries basic company info by name or stock code. It specifies scope (China A-shares) and provides examples. It is distinct from sibling tools focused on financial data.

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

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

The <critical_rules> section explicitly limits to China A-shares, excluding other markets. It explains matching behavior (fuzzy name, exact code) and provides examples. It does not explicitly mention alternatives but siblings are different.

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