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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states what the tool does but does not disclose any side effects, permissions, read-only nature, error behavior, or rate limits. For a retrieval tool, it omits whether it modifies any state or if it requires authentication. This is a significant gap given zero annotation support.

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

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

The description is a single, efficient sentence that front-loads the primary purpose. It avoids redundancy and is appropriately terse. However, its brevity comes at the cost of missing essential context, so it is not a 5, but it is still well-structured and concise.

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

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

With three parameters, an output schema, and no annotations, the description is incomplete. It does not explain what '案例卡' and '通用方法卡' are, what the context is used for, or how the returned data is structured (though output schema exists, the description doesn't orient the agent). An agent cannot fully assess whether this is the correct tool without additional context about the domain or use case.

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

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

Schema description coverage is 0%, so the description must compensate by explaining the parameters. It indirectly references case_id via '按题号' but does not explain the meaning or format of case_id, limit, or query. The query parameter has a default that suggests a use case, but the description does not elaborate. The description adds little value beyond the bare schema names.

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

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

The description states a clear verb '取得' (get/retrieve) and a specific resource: '案例卡与通用方法卡组成的上下文' (context composed of case card and general method card). It also specifies the key selector '按题号' (by question number), which maps to case_id. While it does not explicitly distinguish from siblings, the resource is unique and the tool name reinforces the purpose, so it is clearly differentiated from generic search or document 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 no guidance on when to use this tool versus its siblings (rag_search, rag_get_document, etc.). It does not mention alternatives, prerequisites, or conditions under which this tool is preferred. The only hint is the specific resource it returns, but that is implicit and not explicitly stated as a selection criterion.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the key constraint of rejecting unregistered paths, which is useful. However, it does not mention any other behaviors such as output format, error handling, 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.

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

The description is a single sentence with no wasted words. It front-loads the action and includes the critical constraint, making it concise and well-structured for the information it conveys.

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

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

Given the absence of parameter semantics and usage guidance, the description is incomplete. It does not clarify how to use the parameters or when to choose this tool over siblings, leaving the agent without essential context for correct invocation.

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

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

Schema description coverage is 0%, so the description must compensate for missing parameter documentation. It does not explain what source_file represents or what max_chars does, leaving both parameters entirely undocumented.

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

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

The description clearly states the tool reads text-type public corpus registered in the manifest, with an explicit constraint that unregistered paths are rejected. This specific verb+resource combination distinguishes it from siblings like rag_search or rag_list_sources.

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

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

No guidance is provided on when to use this tool versus alternatives. It implies the user should have a specific source_file path, but does not mention alternatives or conditions for using rag_search or rag_get_case_context.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It conveys that the tool returns status information, implying a read-only operation, but it does not explain whether local indexes are refreshed, whether state may be stale, or whether any side effects occur.

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

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

The description is a single concise sentence that names the three types of status returned. It contains no filler, repetition, or irrelevant details.

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

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

For a parameterless status-check tool with an output schema defined, the description is largely complete. It names the domains whose status is returned; the only minor gap is a lack of elaboration on what '本地生成索引' specifically covers, but this is not critical given the tool's simplicity.

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

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

The tool takes zero parameters, so there is no parameter ambiguity to resolve. The baseline of 4 applies because no parameter descriptions are needed.

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

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

The description states a specific action (返回/returns) and a clear scope: status of corpus, manifest, and locally generated indexes. This clearly differentiates it from sibling tools like rag_search or rag_get_document, which perform different operations.

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

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

No guidance is provided on when to call this tool instead of alternatives such as rag_health or rag_list_sources. The agent must infer its role from the name and description alone.

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

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

No annotations are provided, so the description carries the full burden of disclosure. It usefully reveals that deep=true executes a real retrieval probe, which implies potential cost or side effects. However, it does not describe the output format, whether the probe mutates state, or any failure behavior — gaps that matter more given zero annotation coverage.

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

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

One compact sentence (split by a semicolon) that front-loads the core purpose and appends the parameter behavior. Zero wasted words; appropriately sized for a simple one-parameter health-check tool.

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

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

The tool has an output schema, so return values need no description, and complexity is low with a single optional parameter. The main gap is the unresolved overlap with sibling rag_get_status, which the description does nothing to clarify. Adequate but not complete.

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

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

Schema description coverage is 0%, so the description must compensate, and it does: it explains that deep=true triggers an additional real retrieval probe, adding meaning beyond the bare boolean schema entry. This satisfies the compensation requirement for the single parameter.

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

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

The description states a specific verb and resource: checking paths and indexes of the RAG system. It is not a tautology and adds the deep-mode behavior. However, it does not differentiate from the sibling rag_get_status, which likely overlaps in health/status checking, so it misses the chance to distinguish itself.

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

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

No guidance on when to use this tool versus rag_get_status or the other siblings. The deep=true explanation describes a mode of this tool, not a routing decision. There are no when/when-not conditions or alternative mentions.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It implies a read-only operation ('list') but does not explicitly state that it has no side effects, requires no special permissions, or how it behaves with edge cases (e.g., empty manifest, large result sets). It adds minimal behavioral context beyond the verb.

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

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

The description is a single, efficient sentence that front-loads the core purpose and lists the output fields. It contains no filler or redundancy, making it appropriately concise for a straightforward listing 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?

For a tool with 4 optional parameters and no schema-level descriptions, the description is insufficient. It does not explain parameter semantics, return format (though output schema exists, its details are not shown), or any usage constraints. An agent would struggle to correctly invoke this tool without additional context.

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

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

The schema has 0% description coverage for parameters, and the description does not explain any of the four parameters (layer, limit, case_id, index_default). It does not clarify their purpose, valid values, or how they filter or paginate results. The description fails to compensate for the schema's lack of parameter documentation.

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

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

The description clearly states a specific verb ('list') and resource ('sources in the manifest') with attributes (licenses, layers, question numbers, URLs, hashes). It distinguishes itself from sibling tools like rag_search (search) and rag_get_document (get single document) by indicating a listing operation.

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

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

No guidance on when to use this tool vs alternatives. It does not mention prerequisites, typical use cases, or cases where another sibling (e.g., rag_search) would be more appropriate. The description is purely functional, leaving usage to the agent's inference.

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

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

No annotations are present, so the description carries full responsibility for behavioral disclosure. It mentions the corpus is '公开' (public), implying a safe read operation, but gives no details on rate limits, authentication, pagination, or any side effects. Since this is a search operation that is presumably read-only, the lack of explicit behavioral context is a notable gap.

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

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

The description is a single, compact sentence that front-loads the primary action and then lists the filtering options. There is no redundant wording or unnecessary detail. It is efficient and easy to scan.

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

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

Given the presence of an output schema, return values are covered, so the description need not explain them. However, for a search tool with 5 parameters and no annotations, the description leaves out usage context (when to use vs. siblings) and only vaguely explains the filter semantics. It does not specify the expected format of 'layer' or 'doc_type' values, and does not mention default behavior or limits. This is adequate for a basic tool but not comprehensive.

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

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

The schema description coverage is 0%, so the description must compensate. It explains the meaning of three parameters (题号=case_id, 层级=layer, 文档类型=doc_type) as filters, which adds value beyond the generic schema titles. However, it does not explain the 'limit' parameter, and 'query' is self-evident but not explicitly described. The description partially compensates for the coverage gap.

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

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

The description clearly states the tool's function: '检索国赛优化与决策类公开语料' (retrieve public corpus for national competition optimization and decision-making). It names the specific verb '检索' (retrieve), the resource (public corpus), and immediately lists the filtering dimensions (case number, level, document type), which distinguishes it from sibling tools like rag_get_document or rag_list_sources that target specific items rather than search.

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

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

No guidance is provided on when to use this tool versus its siblings. The description mentions filtering capabilities but does not state any conditions that would favor this over rag_get_case_context or rag_get_document, nor does it mention any exclusions or alternative tools. An agent would have to infer the appropriate use 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.