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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states that the tool returns collection statistics, without confirming it is read-only, safe, or clarifying any side effects, auth requirements, or error handling. 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.

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

The description is a single short sentence, which is concise and front-loaded. However, it could be more structured by explicitly listing the parameters or adding a brief usage note. It is efficient but not maximally informative.

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

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

The tool is simple, and an output schema exists, so the description does not need to explain return values. However, the description omits the token parameter entirely and lacks usage guidelines, making it incomplete for an agent to fully understand the tool's capabilities. It provides the core purpose but not enough context for correct invocation in all scenarios.

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 50% (only prefix has a description). The tool description adds a concrete example for prefix ('如 'T'') and rephrases the schema description, but it does not explain the token parameter at all. While the example adds value, the missing token documentation leaves a 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 verb 'browse' (浏览) and resource 'Chinese Library Classification' (中图法分类), with the specific action of passing a classification prefix and returning collection statistics. It distinguishes itself from sibling tools like search_books and get_book_detail by focusing on classification-based browsing.

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

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

The description implies when to use the tool: when you have a classification prefix to browse. However, it does not explicitly state when not to use it or provide alternatives, such as using search_books for keyword searches. The context of sibling tools provides some implicit guidance, but the description lacks direct usage instructions.

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 behavioral burden. It conveys the tool is a read-only query for availability, which is reasonable. However, it does not disclose details such as whether it returns full availability per branch, pagination behavior, or rate limiting. With no annotations, more transparency would be beneficial.

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

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

The description is a single, concise sentence that front-loads the core purpose. It uses common separators (slashes) to list alternatives clearly. Every word contributes meaning without redundancy.

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

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

Given the tool has moderate complexity (4 params, 0 required) and an output schema exists (agents can infer return format from there), the description adequately covers the core purpose. It does not explain the token parameter or the exact response structure, but the output schema compensates. Minor gap is the lack of hint about how multiple search criteria interact (e.g., AND vs OR).

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 high at 75%, so the schema already documents ISBN, title, and barcode semantics well. The description repeats the search fields but adds no additional parameter-level guidance beyond what the schema provides. The token parameter's role remains unclear from both schema and description, preventing a higher score.

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 this tool queries library copy availability by ISBN, barcode, or title. It uses a specific verb-resource combination ('查询馆藏复本在馆状态') that distinguishes it from siblings like search_books or get_book_detail.

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

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

The description implies usage context—to check availability—and the input schema provides a hint that for title queries with an Oracle backend, search_books should be used instead. However, there is no explicit when-to-use vs. when-not-to-use guidance for ISBN or barcode searches versus other 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?

No annotations are present, so the description carries full burden. It states data retrieval but does not disclose whether this is a read-only operation, any authentication requirements, rate limits, or side effects. The behavioral disclosure is minimal and relies on inference.

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

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

The description is a single, front-loaded sentence with zero waste. Every part contributes to defining the tool's purpose and key outputs.

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 and the tool's focused purpose (retrieve single book details with copy status and circulation), the description is largely complete. It could benefit from including when to use and behavioral notes, but is still adequate.

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 50% (one param documented, one not). The description adds no explanation for the undocumented 'token' parameter and does not elaborate on parameter semantics beyond what the schema provides. It does not compensate for the 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 specifies the verb (获取/get), the resource (单册书目完整信息/complete information of a single book), and explicitly lists included data (馆藏复本状态与流通统计). This uniquely distinguishes it from sibling tools like search_books, get_availability, and get_statistics.

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

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

The description implies usage when complete single-book info with copy status and circulation is needed, but provides no explicit guidance on when to use this tool vs alternatives, nor any prerequisites or exclusions.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not mention side effects, authentication needs, rate limits, data freshness, or pagination behavior. The token parameter is left unexplained, and the description assumes a read-only ranking but does not explicitly confirm safety or data source.

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 Chinese sentence that states the core function and filtering capability. It is front-loaded with the key purpose and has zero wasted words, making it easy for an agent to parse quickly.

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 (which presumably defines the return format), a simple parameter list with defaults, and a straightforward ranking task, the description covers the essential use case. However, it omits details like output ordering, how 'hot' is determined, and token handling, but the output schema may address some of this. It is nearly complete 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.

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

Schema description coverage is 75% with top_n, cls_no, and period having Chinese descriptions that specify constraints (≤50, prefix, total/year). The description adds minimal extra value beyond the schema by mentioning classification filtering, but token remains undocumented. Baseline is 3 due to high coverage, and no substantial semantic enrichment is provided.

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 a ranking of hot borrowed books ('热门借阅图书排行') with optional filtering by Chinese library classification ('可按中图法大类过滤'). This directly distinguishes it from siblings like search_books (general search), get_new_arrivals (new arrivals), and browse_classification (browsing taxonomy) by focusing on popularity ranking.

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

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

The description implies the tool is for obtaining a hot borrowing list with optional classification filtering, but it provides no explicit guidance on when to use it versus alternatives like search_books or get_statistics. There is no mention of prerequisites, auth requirements (despite the token parameter), or when not to use this tool.

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

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

No annotations are present, so the description must fully disclose behavioral traits. The one-sentence description only states the tool's purpose; it does not mention whether it is a read-only operation, pagination, authentication requirements, or any side effects. This is insufficient for an agent to understand behavior.

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

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

The description is extremely concise (one sentence), which is efficient but lacks essential details. It is not structured with front-loading or bullet points. While brevity is valued, it sacrifices clarity and completeness.

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 the presence of an output schema, the description is too minimal to provide complete context. It does not explain what the output represents, how the parameters modify behavior, or any edge cases. For a tool with three parameters and no annotations, the description is insufficient.

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

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

The description adds no information about the three parameters. Although schema coverage is 67% (two parameters have descriptions in the schema), the tool description does not explain how 'clc' or 'days' affect results, and the 'token' parameter remains undocumented. The description fails to compensate for the missing schema description.

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

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

The description '近 N 天新书通报' (new book announcements for the last N days) clearly indicates the tool retrieves recently added books. The verb 'get' is implied by the name, and the resource is 'new arrivals'. While it is distinct from siblings like search_books or get_hot_books, it does not explicitly differentiate its scope or usage.

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

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

No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, context, or exclusions (e.g., when to use search_books instead). An agent has no information about the appropriate use case.

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

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It mentions the admin token requirement but fails to describe the response format, rate limits, or data privacy implications (e.g., the 'include_pii' parameter suggests sensitive data handling). With no annotations, crucial behavioral details like read-only nature or possible errors are missing.

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

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

The description is very concise (one short sentence) with no redundancy. It front-loads the core purpose ('读者当前借阅') and adds the critical auth requirement. However, it could be slightly more structured (e.g., separated into purpose and usage note) without losing brevity.

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

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

Given the tool has 3 parameters (with 67% schema coverage), an output schema, and a clear sibling set, the description adequately signals the core function and auth need. However, it doesn't explain the return format or what happens when the token is missing, but the output schema likely covers return values. The complexity is moderate, and the description almost fully compensates for missing annotations.

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 67% (2 of 3 parameters have descriptions: 'cert_id' is described as '读者证件号 CERT_ID', and 'include_pii' has a clear explanation). The description adds context about the token being an admin auth requirement, which complements the schema. The 'include_pii' parameter's description in the schema is already informative, and the tool name implies purpose, so the remaining gap is minimal.

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 explicitly states '读者当前借阅' (reader's current borrowing) with the specific verb 'get' implied by the tool name and '需 admin 认证令牌' (requires admin auth token). It clearly distinguishes from siblings like 'get_reader_history' (historical borrowing) and 'get_reader_fines' (fines), making it unique among reader-related tools.

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

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

The description mentions the need for an admin token and implies this is for current borrowing status. However, it does not explicitly exclude when to use alternatives like 'get_reader_history' for past records, nor does it provide clear context on prerequisites beyond the token. Still, the admin token requirement is a strong usage signal that helps the agent decide when to invoke this tool.

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

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

No annotations are provided, so the description must fully disclose behavioral traits. It mentions the need for an admin token, which hints at security/permission behavior. It does not disclose whether the operation is read-only, destructive, or has side effects. The parameter include_pii with default false suggests privacy behavior (data masking), but this is not explained in the description. With no annotations, a score of 3 reflects partial disclosure.

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

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

The description is extremely concise (one short sentence in Chinese with a parenthetical note). It front-loads the core purpose and an important constraint. It could be slightly more structured or include an English explanation, but for a bilingual context it is efficient.

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

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

Given the tool has an output schema (so return values don't need explaining), 3 parameters, and no annotations, the description covers the core purpose and one critical constraint (admin token). It does not explain why include_pii exists or how to handle errors, but with the output schema and moderate complexity, this is reasonably complete.

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

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

Schema description coverage is 67% (2 out of 3 parameters documented: cert_id and include_pii). The description adds value beyond the schema by stating '需 admin 认证令牌' which implies the token parameter must be supplied with an admin-level token. It does not describe cert_id semantics further, but the schema already does that. The missing parameter (token) is implicitly addressed by the authentication hint in the description.

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

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

The description uses Chinese to state '读者欠款 / 罚款明细' meaning 'reader fines/fee details', which clearly indicates retrieving fine details for a reader. This distinguishes the tool from siblings like get_reader_borrowing (borrowing records) and get_reader_history (reading history). However, the verb is implicit, so it is not a perfect 5.

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

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

The description adds '需 admin 认证令牌' meaning 'requires admin authentication token', which implies when to use the tool (must have admin rights). However, it provides no guidance on when not to use this tool or how it compares to siblings like get_statistics or union_search. The only usage hint is the authentication requirement, which is insufficient for an agent deciding among 12 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?

No annotations are provided, so the description bears full responsibility. It states 'requires admin authentication token' but does not disclose whether the tool is read-only, what data it returns (history, pagination, etc.), or any potential side effects. This is insufficient for safe agent invocation.

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

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

The description is a single, front-loaded sentence. It conveys purpose and the critical admin requirement without wasted words. However, it is extremely brief, bordering on under specification, which reduces the score from 5.

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

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

Despite having 3 parameters, an output schema, and no annotations, the description only covers purpose and auth. It omits usage context, parameter guidance, and behavioral traits like read-only nature. For a tool with moderate complexity, this is incomplete.

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

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

Schema coverage is 67% (2 of 3 parameters have descriptions in the schema). The description adds no parameter information, such as explaining what cert_id represents or when include_pii should be true. Given moderate coverage, the description should at least echo parameter roles, which it fails to do.

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 '读者借阅历史' clearly identifies the tool as retrieving a reader's borrowing history. It includes the admin authentication requirement, adding specificity. However, it does not explicitly distinguish from sibling get_reader_borrowing, which likely handles current borrows. The Chinese-only phrasing may limit understanding for non-Chinese agents, but the purpose is unambiguous.

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

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

No guidance on when to use this versus siblings like get_reader_borrowing or get_reader_fines. The only usage hint is the admin auth requirement, which is a prerequisite, not a selection criterion. An agent would need to infer from the name alone.

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

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

No annotations are present, so the description carries the full burden of behavioral disclosure. It does not state whether the tool is read-only, requires authentication, has rate limits, or any side effects. The single phrase offers no transparency beyond a vague topic.

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

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

The description is extremely short (four characters) but under-specified. It does not earn its place because it provides almost no useful information. True conciseness requires meaningful content, not mere brevity.

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

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

Given the tool has three parameters, an output schema, and multiple sibling tools, the description is grossly incomplete. It does not explain the return structure, parameter usage, or how to interpret the output. The agent cannot infer proper usage from this description alone.

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

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

The description adds no meaning beyond the input schema. The schema already describes two of three parameters (metric and range_desc) with explicit options; the description does not summarize or clarify them. The token parameter lacks a schema description and the tool description does not help either. With 67% schema coverage, the description should compensate but fails to do so.

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 '馆藏统计' (collection statistics) gives a vague sense of the tool's domain but lacks a specific verb or action. It does not clarify what the tool returns or how it differs from sibling tools like search_books or get_availability. The purpose is only marginally clearer than the tool name 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 is provided on when to use this tool versus alternatives. There is no mention of context, prerequisites, or when not to use it. The description does not hint at any selective use cases, leaving the agent without decision support.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states that it returns health status, but does not mention whether the optional token parameter is used for authentication, whether any side effects exist, or how health is determined. The behavior remains largely opaque beyond the basic return.

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

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

The description is a single, front-loaded sentence with no filler, stating the core purpose efficiently. It is appropriately sized for a simple status tool, though it omits some detail. The structure is clean and direct.

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 the simplicity of the tool (one optional parameter, output schema present), the description is incomplete because it fails to explain the token parameter and provides no behavioral context. The output schema mitigates return-format uncertainty, but the agent lacks enough information to confidently invoke the tool correctly.

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

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

The input schema description coverage is 0%, and the description does not mention the 'token' parameter at all. The schema shows it is an optional string or null, but its purpose (e.g., authentication, context) is completely unexplained, leaving the agent to guess how to use it.

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

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

The description '返回当前数据源与后端健康状态。' clearly states a specific verb ('返回' = returns) and resource ('数据源与后端健康状态' = data source and backend health status). This distinct purpose sets it apart from sibling tools like search_books and get_book_detail, which are book-related queries.

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

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

No explicit usage guidance or alternatives are provided. The purpose implies a system health check, and sibling tools are all book-related, which makes the intended usage inferable, but the description does not state when to use this tool (e.g., 'to verify backend health') or contrast it with alternatives.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states 'search' and lists output fields, which implies a read-only operation but does not explicitly declare it. It does not mention authentication requirements, rate limits, side effects, or any constraints. For a search tool with 11 parameters, 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.

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

The description is extremely concise: two sentences. The first sentence states the primary action, and the second lists the returned fields. Every word is functional, and the structure is front-loaded. There is no redundancy or filler.

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

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

Given the tool has 11 parameters, an output schema exists, and there are 12 sibling tools, the description is too minimal. It does not explain pagination, field-specific search, date filtering, location filtering, or the token parameter. The agent would lack essential context to use the tool effectively, especially for non-trivial queries.

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

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

The description adds no information about any of the 11 parameters. Schema coverage is 55% (6 parameters have descriptions in the schema), but the description does not compensate for the 5 parameters without descriptions (page, page_size, pub_year_min, pub_year_max, token). It also does not explain how the query parameter is interpreted (e.g., keyword matching, Boolean operators). The output description is helpful but does not aid parameter usage.

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 core function: searching the library catalog and returning a list of specific fields (title, author, publisher, ISBN, location, availability). The verb '检索' (search) is specific and the resource '馆藏书目' (library catalog) is well-defined. While it does not explicitly distinguish from siblings, the sibling tools are mostly specialized (detail, availability, hot, new, classification), making this the general search tool.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, exclusions, or specific contexts. With 12 sibling tools including get_book_detail, browse_classification, and union_search, the lack of differentiation or usage hints leaves the agent to infer usage from the name alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states the tool is read-only, requires configuration, and returns clear prompts when improperly configured. It does not elaborate on authentication failures or performance, but the reference to external documentation partly compensates for these gaps.

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

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

The description is efficiently structured with three sentences that front-load the purpose, then cover prerequisites and behavioral notes. It is concise and to the point, though it could benefit from slight restructuring (e.g., bullet points for configuration) without adding length.

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

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

Given the tool's complexity (cross-library search, configuration requirements, read-only), the description covers the essential aspects: purpose, prerequisites, behavioral traits, and error handling. The presence of an output schema mitigates the need for return value details. It is sufficiently complete for an agent to understand the tool's role and constraints.

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 50%, meaning half of the parameters lack descriptions in the schema. The tool description adds meaningful context: it explains the token parameter as a reader session JWT, outlines configuration dependencies, and clarifies the query parameter's multi-value behavior. This adds value beyond the raw schema, although a full parameter breakdown is absent.

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 as a cross-library union catalog search ('跨馆联盟联合目录检索'), specifying it as an external PROCAT service for OPAC results. This is a specific verb-resource combination that distinguishes it from sibling tools like search_books, which likely target a single library catalogue.

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 clear prerequisites (requires configuration flags and a JWT token) and declares its read-only nature ('仅只读检索'), clarifying what it does not do (no inter-library loan ordering). While it does not explicitly compare to sibling tools, the context signals infer its specialized use case, and the description mentions an external documentation reference for further detail.

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