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

With no annotations, the description carries the full burden. It discloses the extraction pattern, per-citation verification, and return counts, but omits whether the operation is read-only, requires network access, has rate limits, or has other side effects. For a verification tool, this is adequate but incomplete.

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

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

The description is front-loaded with the core purpose and uses clear Args/Returns structure. It is slightly verbose but every section contributes useful information for calling the tool correctly.

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

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

For a simple one-parameter tool with no output schema, the description covers purpose, usage, input semantics, and a summary of return values. It could mention edge cases (e.g., no citations found) or output shape more precisely, but it is largely complete.

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

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

Schema description coverage is 0%, so the description must compensate. It explains that the single parameter is the text to check and gives a helpful example (model output legal analysis), which adds meaning beyond the bare schema type.

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: extract all 《法律》第 N 条 citations from a text, verify them one by one, and return the list of non-existent citations. It clearly distinguishes itself from siblings like search_statutes and list_laws, though it does not explicitly name the alternative verify_citation for single-citation checking.

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?

It gives clear context by instructing to pass an entire model-generated answer to discover fabricated citations. This tells the agent when the tool is useful, but it does not mention exclusions or explicitly compare against sibling tools like verify_citation.

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

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that found articles include 编章, 部门法, and 时效状态, and that the tool returns None when not found, but it does not state read-only nature, permissions, rate limits, or other operational behavior.

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

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

The description is front-loaded with the purpose, then uses compact Args and Returns sections. Every sentence earns its place, and the examples clarify accepted input formats without waste.

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

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

For a two-parameter retrieval tool with an output schema, the description covers both inputs and the fallback return behavior. It lacks routing guidance to sibling tools, but nothing required to invoke the tool correctly is missing.

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

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

Schema description coverage is 0%, so the description must compensate. It does so by documenting both parameters: law supports abbreviations with examples, and article_no accepts Chinese or Arabic numerals with examples.

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: retrieve the original text of a legal article by law name and article number. This is clear, but it does not explicitly differentiate itself from siblings such as search_statutes or verify_citation.

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

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

There is no explicit when-to-use guidance, no mention of when to prefer search_statutes or other siblings, and no exclusions. Usage is only implied by the required parameters.

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. '浏览' implies a read-only operation and the limit default is stated, but there is no explicit confirmation of read-only behavior, side effects, or authentication needs.

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 purpose is front-loaded in one sentence, followed by a compact Args section. Every sentence adds useful information with no filler.

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

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

For a simple list tool with an output schema, the description covers purpose and all parameters adequately. It does not explicitly state that no filters returns all laws up to the limit, nor any ordering or pagination behavior beyond the limit.

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

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

Schema description coverage is 0%, so the description must compensate. It explains all three parameters with examples for keyword and department, and restates the limit default, adding clear meaning beyond the bare 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 states a specific verb and resource: browsing the law catalog, with optional filters by name keyword or department. It is clear what the tool does, but it does not differentiate itself from siblings like search_statutes or get_article.

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?

It implies usage for browsing/filtering laws, but gives no explicit when-to-use versus alternatives such as search_statutes. There are no exclusions or conditions for choosing this tool over its 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?

With no annotations, the description carries the full burden and discloses meaningful behavior: automatic expansion into legal language, direct citation lookup priority, and returned fields including score and via. It still omits permissions, ranking behavior, coverage limits, and the precise meaning of score/via.

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?

Structured as purpose, usage, Args, and Returns, with the core purpose front-loaded. There is slight redundancy between the introductory query-mode text and the query argument, but every section helps callers.

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 3-parameter search tool with an output schema, the description covers query modes, parameter meanings, and return fields. It omits explicit sibling routing, which is a minor gap but not an invocation blocker.

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: query is defined as natural-language question or keywords, top_k defaults to 6, and law is optional with abbreviation support such as 民法典/消保法. All three visible parameters receive useful semantic detail beyond the bare 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?

States a specific verb (检索) and resource (中国现行法律条文), and clarifies supported query modes such as自然语言 and precise citation. Sibling differentiation is implicit rather than explicit; it does not name or contrast get_article/list_laws.

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?

Gives clear usage contexts: colloquial questions, keyword queries, and exact statutory citations with direct-lookup priority. It does not say when to prefer sibling tools like get_article or verify_citation, and offers no exclusions.

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

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

No annotations exist, so the description carries the full burden. It discloses the return contract (verified bool plus 条文原文 or 原因) and the anti-hallucination purpose, which is useful, but it says nothing about read-only safety, permissions, or rate limits.

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?

Front-loaded purpose sentence, then a usage cue, then Args and Returns. Every section earns its place and nothing is padded, though the Args/Returns blocks partially restate schema structure.

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

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

With no output schema and 0% schema coverage, the description correctly fills both gaps by documenting parameter formats and the return shape. It is complete enough to invoke correctly, missing only edge-case behavior (e.g. what 'reason' values look like).

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

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

Schema description coverage is 0%, so the description must compensate, and it does: law supports abbreviations (「民法典」) and article_no accepts both Arabic and Chinese numerals («1254» or «第一千二百五十四条»). These format details are genuinely beyond the bare 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?

States a specific verb+resource ('核验一条法律引用是否真实存在') and adds the intent (防幻觉), so an agent immediately knows this is an existence-check rather than a retrieval tool. It does not explicitly name how it differs from siblings like get_article or check_citations_in_text, which keeps it below a 5.

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

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

Gives a clear triggering condition: call before citing 《某法》第 N 条 to avoid fabricating or citing repealed articles. This is explicit 'when to use' guidance. It lacks explicit 'when not to use' or a named alternative sibling, so it falls short of a 5.

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