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

With no annotations, the description fails to disclose behavioral traits like side effects, permissions, or return behaviors. It only says 'route' without detailing the routing mechanism or output.

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 communicates the core action without extraneous words.

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 an output schema (not detailed here), the description omits return behavior, side effects, and how the output relates to routing. It is insufficient for a tool in a complex domain with many siblings.

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 sole parameter 'question_text' is self-explanatory by name, and the schema has no descriptions. The description adds no further meaning, but given only one parameter, the agent can infer its purpose.

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 routes a question stem to preliminary modules and method cards, specifying a verb and resource. However, 'preliminary modules' is somewhat vague, and the tool's exact function could be more distinct from siblings like route_xingce_question.

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 alternatives such as route_xingce_question or search_methods. The description lacks context about prerequisites or scenarios.

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 full burden. It clearly states the tool does not solve questions, compute answers, or select options, and returns prompt_text for LLM consumption. This provides good insight into its behavior and limitations.

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 two concise sentences with front-loaded purpose, clear exclusions, and no wasted words. Excellent 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?

The description adequately conveys the core function, but fails to explain the role of 'route result' (not in schema) and how the tool fits with siblings. Given the output schema exists, return details are acceptable.

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%. The description only explains module_hint and section_context, leaving the purpose of options, strict_mode, image_present, and include_scaffold_summary unclear. This fails to compensate for the lack of schema 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 it composes a structured analysis prompt from question and route result, and explicitly states what it does not do (solve questions, compute answers, or select options). However, it does not differentiate from the sibling 'compose_xingce_answer_prompt' or other scaffold 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 support for module_hint and section_context to guide routing, but does not provide explicit guidance on when to use this tool versus alternatives like scaffold tools or solve 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?

With no annotations provided, the description carries the full burden. It transparently states the tool does not answer questions, call external LLMs, or select options. It also mentions the output includes an answer_prompt with constraints, output schema, and safety contract. However, it does not disclose whether the tool has side effects or is read-only, nor mention any authorization or rate limiting.

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 at three sentences. Each sentence adds value: first states purpose, second lists supported features, third clarifies limitations and output. No unnecessary words or fluff.

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 complexity of 11 parameters and no annotations, the description is incomplete. It fails to explain most parameters, provide usage context, or describe the output schema (though it exists). For a tool with such complexity, the description should cover more ground.

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 only mentions two parameters (module_hint and section_context) as supporting routing, but ignores the other 9 parameters (e.g., options, strict_mode, allow_answer, image_present, material_text, question_text, table_present, material_present, visual_description). This provides almost no added meaning beyond the 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 it composes a conservative answer prompt for LLM-in-the-loop answering and explicitly notes what it does not do (does not answer, call external LLM, select options). It mentions supporting module_hint/section_context. However, it does not explicitly distinguish itself from the sibling tool compose_xingce_analysis_prompt, which could lead to confusion.

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 (e.g., compose_xingce_analysis_prompt, classify_question). It does not state prerequisites, when to prefer this tool, or when not to use it. The only hint is that it supports routing by exam section context, but this is vague.

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?

Describes the tool as read-only and lists its output contents, which provides transparency about its non-destructive nature. However, without annotations, additional behavioral details such as idempotency, rate limits, or authentication requirements are absent. The description is adequate but could be more explicit.

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?

Two sentences concisely convey the tool's purpose, output contents, and limitations. No extraneous information. Front-loaded with the core function.

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 parameters and an existing output schema, the description fully covers the tool's behavior and output. It specifies what is returned and what is not done, making it complete for 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?

No parameters exist, so schema coverage is effectively 100%. The description adds value by detailing the scaffold's components (checklists, steps, comparison guidance, uncertainty policy), which clarifies the nature of the returned content beyond the 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?

Clearly states it returns a 'read-only method scaffold for analogy reasoning' and lists specific components it provides. Differentiates from sibling scaffolds by naming the reasoning type and explicitly stating it does not solve questions or select answers, which separates it from other reasoning 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?

Explicitly states when not to use it ('does not solve questions or select an answer'), implying it is for scaffolding guidance only. While it does not name specific alternatives, the sibling tools list provides context for other reasoning scaffolds, guiding selection based on reasoning domain.

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 full burden, and it states read-only behavior and lists contents, ensuring agent knows it is safe and non-destructive. It lacks details about any potential side effects or permissions, but for a read-only scaffold, 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.

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

The description is concise with two sentences, front-loaded with the action verb 'Return', and every sentence adds value 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 no parameters and presence of an output schema, the description sufficiently explains purpose and components, making it complete for 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 has zero parameters and 100% schema coverage, so the baseline is 4. The description adds no parameter-specific information, which is acceptable since none 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 clearly states the tool returns a read-only method scaffold for definition judgement, lists specific components (polarity routing, checklists, verification template, uncertainty policy), and explicitly distinguishes it from solving tools, making its purpose distinct from siblings like solve_data_analysis.

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 indicates when to use (when needing the scaffold) and what it does not do (does not solve or select answers), providing clear context. However, it does not explicitly name alternative tools for solving, though sibling names imply other scaffolds.

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 takes responsibility. It declares the tool is read-only and lists scaffold components. It also clarifies what the tool does not do. However, it does not describe the output schema or any side effects beyond being read-only.

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 two concise sentences, front-loaded with the core purpose, followed by clarifying details. No extraneous information.

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 no parameters and an output schema exists, the description fully covers what is needed: the tool's function, components, and limitations. It is complete for an agent to understand the tool's role.

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?

There are no parameters, so a baseline score of 4 is appropriate. The description does not need to add parameter details.

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 returns a read-only method scaffold for graphic reasoning, listing specific components and explicitly stating what it does not do, which distinguishes it from sibling scaffold 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 implies usage for getting a scaffold for graphic reasoning but does not explicitly provide when-to-use or when-not-to-use guidance compared to alternative scaffolds. The negative list ('does not inspect images...') provides some context but lacks direct usage recommendations.

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 full burden and describes the tool as 'read-only', implying no side effects. It lists what the scaffold provides but does not detail behavior like rate limits or dependencies. However, it is sufficiently transparent about its purpose and limitations.

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, no superfluous words. The main purpose is front-loaded, and every sentence adds value.

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 zero parameters and a provided output schema, the description covers the essential aspects: what the tool returns and what it does not do. It could mention that the scaffold aids in generating reasoning steps, but overall it is complete enough for an AI agent.

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 has no parameters, so the description trivially adds value beyond schema. Schema description coverage is 100% since no parameters exist, and baseline is 4-5.

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 returns a read-only method scaffold for logic analysis reasoning, listing specific components like problem-type routing and structure templates. It explicitly distinguishes itself by stating what it does not do (solve or select answers), and the purpose aligns with its sibling scaffold 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 implies usage when needing the scaffold for logic analysis reasoning, and clarifies its limitations by stating it does not solve questions or select answers. Although it doesn't explicitly mention when not to use or alternatives, the context is clear enough for an AI agent.

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 behavioral traits are disclosed beyond the bare operation. There are no annotations, and the description does not mention any side effects, permissions, rate limits, or the nature of a 'full method card'.

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 with no extraneous words. However, it could be restructured slightly to include additional context without losing conciseness.

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, the description is not required to detail return values, but it omits any context about what a method card is or how it relates to other tools in the set.

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 0% schema description coverage, the description should explain the parameter 'method_id'. It only mentions it in passing ('by method_id') without defining what constitutes a valid ID or how to obtain one.

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 action ('Return'), the resource ('full method card'), and the specific identifier ('by method_id'). This makes the purpose unambiguous and distinguishes it from sibling tools like 'search_methods' which returns a list.

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, such as 'search_methods' or 'get_source_reference'. It neither specifies prerequisites nor indicates when not to use it.

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 states the tool is read-only and does not solve questions or compute answers, providing good behavioral boundaries despite the absence of annotations. No side effects or auth details are needed for a scaffold.

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 two sentences, front-loaded with the primary action, and every sentence adds value. No waste or 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 zero parameters and an output schema present, the description fully covers what the tool does and does not do. It is complete for its purpose.

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?

No parameters exist, so baseline 4 applies. The description adds no parameter info, which is appropriate since schema coverage is 100% and no params need 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 specifies the tool returns a 'read-only method scaffold' for 'quantity relation reasoning' and lists components (problem-type routing, extraction guidance, etc.), clearly distinguishing it from sibling scaffold tools for other reasoning types.

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 for quantity relation reasoning but does not explicitly state when to use vs. alternatives or provide exclusion criteria. Minimal guidance beyond the name.

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 full responsibility for behavioral disclosure. It indicates a read operation (returning data) but omits details such as authorization requirements, side effects, rate limits, or error conditions. This minimal transparency 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, efficient sentence with no wasted words. It is well front-loaded with the key information. For a simple tool, this is ideal conciseness.

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 simplicity (one parameter) and the presence of an output schema (which likely details return structure), the description is mostly complete. It clearly states what is returned. However, it lacks any mention of pagination, error handling, or limitations, but these are less critical with an output schema.

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 add meaning. The only parameter, method_id, is implied to identify a method, but no format, constraints, or default behavior are specified. The description adds little beyond what the parameter name already conveys.

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 returns source files, pages, confidence, and review flag for a method. It uses a specific verb ('return') and resource ('source reference'), making the purpose clear. However, it does not differentiate itself from similar sibling tools like 'get_method_card' or 'search_methods', missing an opportunity for deeper clarity.

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 any context, prerequisites, or exclusions, leaving the agent without direction on appropriate usage scenarios.

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 fully carries the burden. It explicitly states the tool is read-only and does not solve questions or compute answers, which clearly discloses its behavioral boundaries.

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 two sentences, front-loaded with the main purpose, and every sentence adds value 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?

The tool is simple (zero parameters, no annotations, but has output schema). The description covers what the tool does and what it does not do, which is complete for its intended use.

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 has 0 parameters, so schema coverage is 100%. No parameter description is needed, and the tool's description adds no param info but is not required.

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 returns a 'read-only method scaffold for verbal reasoning' and lists specific features it provides (question-type routing, discourse-structure analysis guidance, etc.), distinguishing it from sibling scaffolds for other reasoning types.

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?

Although no explicit when-to-use or when-not-to-use guidance is given, the domain-specific name and the list of features imply usage for verbal reasoning tasks. The exclusion statement ('does not solve questions') helps set expectations.

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?

Despite no annotations, the description discloses key behaviors: it routes without solving, returns module guess, confidence, recommended tool/track, and reasoning signals. It also clarifies it does not answer questions or select options. No mention of idempotency or auth, but sufficient for a routing tool.

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 primary purpose and consists of three concise sentences with no wasted words. Every sentence adds value (purpose, supported parameters, what it returns, what it does not do).

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 main purpose and behavior well, and with an output schema present, return values are documented elsewhere. However, it lacks parameter explanations for 4 of 6 parameters and does not provide explicit comparison with sibling tools beyond the 'without solving' distinction.

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 0%, so the description must compensate. It only explains module_hint and section_context for guiding routing, covering 2 of 6 parameters. Options, strict_mode, and image_present are not mentioned, leaving significant gaps.

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 routes a question to a recommended module or scaffold without solving. It uses specific verb 'route' and resource 'module or scaffold', and distinguishes itself from siblings like solve_data_analysis and solve_logic_reasoning by explicitly stating it does not solve.

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 clarifies what the tool does and does not do (does not answer or select options), and mentions supported parameters for guiding routing. However, it does not explicitly mention when to use this tool versus alternatives like classify_question, though the distinction from solving tools is clear.

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 disclose behavioral traits. It only says 'search' but does not mention any side effects, permissions, rate limits, or output characteristics.

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, which is concise but lacks structure and front-loading of key information. It is under-specified for the complexity of the 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 the presence of sibling tools and an output schema, the description does not provide enough context. It fails to explain what a 'method card' is or how search results are returned.

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%, and the tool description adds no meaning to the parameters. Users get no insight into how 'query', 'top_k', or 'module' affect the search.

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 action (search) and the resource (method cards in Xingce knowledge base). It distinguishes from sibling tools like 'get_method_card' which suggests retrieval of a specific card.

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. The description only states what it does, without context on scenarios 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 bears full responsibility. It discloses that the tool produces a draft, not a final answer, which is helpful. However, it omits other behavioral traits such as side effects, authentication needs, or whether it is read-only. The single sentence leaves significant 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 very concise (one sentence) and front-loaded. However, it is overly terse and lacks sufficient detail to be helpful. While not verbose, it sacrifices substance for 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?

Despite having an output schema that might specify return values, the description fails to mention it or provide context. The tool's complexity (data analysis solving draft) and lack of parameter documentation mean the description is incomplete for effective use.

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 has 0% description coverage, and the description adds no information about the parameters 'options' or 'question_text'. The agent receives no guidance on what these parameters mean or how to construct them.

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 it builds a structured draft for data analysis solving, distinguishing it from a final answer. However, given sibling tools like 'solve_logic_reasoning' and 'compose_xingce_analysis_prompt', the purpose is not fully differentiated; the verb 'build' and 'draft' are somewhat specific but vague.

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 vs alternatives. No prerequisites, context, or exclusions are mentioned, leaving the agent without direction among many 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?

With no annotations provided, the description must carry the full burden. It only indicates the output is a draft, not final. Missing details on side effects, required permissions, rate limits, or output structure. The behavioral disclosure 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.

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

The description is a single sentence, which is concise but sacrifices informativeness. It could include key details without being verbose. The structure is adequate but not optimized for quick scanning.

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 complexity of logic reasoning and the presence of an output schema, the description is too brief. It does not explain what a 'solving draft' entails, how it relates to other tools, or what the output contains. The description is incomplete for reliable tool use.

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%, and the tool description does not explain any parameters. The meaning of 'question_text' and 'options' is left entirely to the schema, which has no descriptions. This makes it hard for an agent to provide correct input.

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: building a structured logic-reasoning solving draft, and explicitly contrasts it with a final answer. However, it does not distinguish from sibling tools like get_logic_analysis_scaffold, which could cause confusion.

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 alternatives (e.g., get_logic_analysis_scaffold). The description lacks context for selection and does not mention prerequisites or limitations.

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