RoboParts 机器人零部件兼容性

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

With no annotations, the description fully carries the behavioral transparency burden. It discloses that verdicts are rule-based inferences from vendor-declared fields, not physical tests; that undeclared dimensions are marked undetermined; and that it will not fabricate conclusions. It also clarifies the critical meaning of overall_compatible=null as 'insufficient evidence', not 'incompatible', and states that verdict_reason is the authoritative basis.

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, then adds only high-value behavioral caveats: inference vs. testing, no fabricated conclusions, null semantics, and reliance on verdict_reason. Each sentence earns its place; there is no fluff or redundant restatement of the tool name.

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 (pairwise matrix, four dimensions, no output schema, no annotations), the description is unusually complete. It covers what the tool does, how verdicts are derived, how missing data is handled, and how to interpret null results. It even points to the authoritative field (verdict_reason), leaving no major decision ambiguity for the 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 schema already provides 100% parameter coverage, including ID examples, requirement to use search_components, OSS support, and a minimum of 2 IDs. The tool description adds minimal semantics beyond this—mostly repeating 'existing IDs', 'OSS-xxx', and the two-ID minimum. Therefore, the baseline of 3 applies; the schema does the heavy lifting.

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 opens with a specific verb and resource: '对一组零部件做两两兼容性矩阵' (perform pairwise compatibility matrix on a BOM), clearly distinguishing this from the generic sibling check_compatibility. It also names the four evaluation dimensions (protocol/electrical/mechanical/software) and the return type, making the tool's scope unmistakable.

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 and schema give clear usage context: IDs must already exist, should be obtained via search_components, OSS-xxx entries are allowed, and at least 2 IDs are needed for meaningful results. It does not explicitly state when not to use this tool versus the sibling check_compatibility, so a small exclusionary gap remains.

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 and does a good job: it explicitly states conclusions are rule-based on manufacturer public declarations, not lab-tested, and that undeclared dimensions are marked as 'cannot determine' and not counted as compatible/incompatible. This is valuable behavioral context for an agent interpreting results, though it does not cover authentication or side effects, which are likely less relevant here.

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: the first states the main purpose and return types, the second delivers an important caveat about inference basis and undeclared dimensions. It is front-loaded, every sentence adds value, and there is no redundant or vague wording.

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 a 2-parameter tool with no output schema, the description sufficiently explains the core behavior: what it returns (per-dimension, overall, confidence) and the inference logic. It lacks a concrete output format example, but the stated return categories and the detailed parameter schema make the tool actionable. A fully exhaustive spec would be excessive for this 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?

Schema description coverage is 100%, so the baseline is 3. The description itself does not add parameter-specific semantics beyond the schema, which already thoroughly explains ID format, retrieval via search_components, and the ID-prefix mismatch warning. The description's mention of the four dimensions is context for the tool's logic, not parameter syntax, so it does not elevate the 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 uses the specific verb '判定' (determine) and clearly identifies the resource: compatibility of two components across four stated dimensions (protocol/electrical/mechanical/software). It also lists what the tool returns (per-dimension conclusions, overall judgment, confidence), distinguishing it from sibling tools like get_component_detail or recommend_for_application.

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 cross-component compatibility checking and even notes in the parameter schema that cross-category comparison is this tool's purpose. However, it does not explicitly state when to use this tool versus alternatives or provide exclusion criteria, though the context is clear enough for an agent to infer appropriate use.

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 behavioral disclosure burden. It does well by revealing that missing fields render as null (not implying unsupported features), that identical values are auto-annotated, and that cross-vendor comparisons need semantic normalization. It does not describe the output format, but the side-by-side comparison behavior is reasonably transparent.

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

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

The description is a single compact sentence that front-loads the core purpose, then adds the key behavioral caveats and cross-vendor usage note. Every clause earns its place; there is no fluff or repetition of schema details.

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

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

For a single-parameter comparison tool with no output schema, the description covers the essential operational context: scope, parameters, null semantics, and when to use companion tools. The only notable gap is the lack of an explicit statement about the return shape, but the side-by-side comparison concept and auto-annotation hint make the tool sufficiently callable.

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 100%: the ids parameter already includes array shape, min/max, example format, and the instruction to use search_components first. The tool description adds the 2~6 range and example IDs, but this largely restates schema content rather than adding new semantic meaning. Baseline 3 is appropriate.

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 ('并排对比' / side-by-side compare), a concrete resource (零部件 / components), a scope (2~6 items), and lists the exact parameters compared (torque/speed/voltage/protocol/interface/weight/price). It also explicitly differentiates itself from get_component_detail by saying it replaces repeated calls for the same purpose.

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 directly names the alternative tool (get_component_detail) and explains when compare_components is preferable. It also gives a conditional usage rule: for cross-vendor numerical comparisons, pair with get_parameter_semantics. The schema additionally instructs the agent to confirm IDs via search_components, providing clear routing guidance.

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 and does substantial work: it declares read-only, no-auth behavior and enumerates the returned verdict structure (overall status, per-axis rulings with reasons, three-layer attribution L1→L2→L3). It does not discuss failure modes, error responses, or cost/latency, which keeps it short of a 5 for a no-annotation 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?

Front-loaded with a bracketed scope header that immediately frames the tool, then the verb/resource, then usage examples, then the critical caveat. It is dense with parentheticals and layer notation, but each clause carries distinct information (outputs, use cases, dimension warning) rather than repetition.

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?

There is no output schema, so the description must explain return values itself — and it does, enumerating overall verdict, per-axis adjudication with reasons, and the three-layer composed attribution. Combined with the explicit scope/caliber caveat versus check_compatibility, an agent has everything needed to call it 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?

Schema description coverage is 100%, so the schema already documents both parameters, including the component1_id format hint and the search_components prerequisite. The description's only added semantic is that omitting component2_id returns library-level aggregation, which the schema states verbatim, so it adds no meaning beyond the structured fields.

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 and resource: it queries the RoboParts three-axis composition verdict (mechanical/electrical/signal), naming exactly which outputs it produces (overall composed/type_error/unknown, per-axis verdicts, attribution layers). It also explicitly distinguishes itself from the sibling check_compatibility by dimension, so an agent can tell them apart without inspecting schemas.

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 lists the questions it answers ("why was this pair judged type_error", "which pairs can actually be assembled", "is composed=0 a data gap or a relation-type issue") and names the alternative tool plus the condition under which its dimension differs (signal role complementarity vs. check_compatibility's protocol bus + ROS2). It even warns the two outputs must not be mixed, which is a clear when-not-to-substitute rule.

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 and does disclose the safety profile ('只读、免鉴权' – read-only, no auth required) plus the nature of the content returned. It stops short of describing return format, pagination, or how many records are returned, but for a zero-parameter lookup this is a solid 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?

Front-loads a scope marker ('研究层口径') and the core resource, then adds example questions and the safety line. Dense but every clause contributes – the scope marker, the returned artifacts, the example questions, and the read-only/no-auth note all earn their place. 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?

Given zero parameters, no annotations, and no output schema, the description does the necessary work: it names what is returned, supplies example queries, and states the safety profile. The only gap is the absence of any routing guidance against the many compatibility siblings, which is the main ambiguity an agent would face.

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

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

The tool takes zero parameters, so the baseline is 4; there is no input surface for the description to clarify. Schema coverage is reported at 100% and the description correctly implies a fixed, no-argument query shape.

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 (查询/query) and resource (连接器取证与类型判据 – connector forensics and type criteria), and names the concrete artifacts returned: verified connectors (pins/pinout/power), non-intermatable variant cases, and the (family, pins, pinout) triple criteria. It is distinguishable from the compat-check siblings (check_compatibility, review_compatibility) by being explanatory rather than evaluative, though that differentiation is implied rather than stated.

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 context via three concrete example questions ('can these two mate', 'why incompatible despite both being M8', 'what does null pinout mean'), which tells the agent the intended query shape. It does not, however, explicitly name alternatives or state when NOT to use this tool versus check_compatibility/bom_compatibility_check, which is the natural ambiguity given the overlapping sibling set.

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 burden. It discloses 只读、免鉴权, which are useful safety traits, but does not describe output format, determinism, or rate limits. This is basic behavioral disclosure 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?

Front-loads the core purpose and then gives usage examples and a safety note. Dense but mostly earned; the multiple example questions are useful for routing but make it slightly longer than a minimal definition.

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 0-param, read-only explanation tool with no output schema or annotations, it provides purpose, example triggers, and safety traits. Return format is unspecified, but no output schema exists and the description needn't explain return values.

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 0 parameters, so the rubric baseline is 4. The schema is empty and the description adds no parameter semantics because none exist.

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 (查询) and resource (最小可行同质集取证判据), then lists concrete sub-questions it answers. The purpose is clear, but it does not explicitly distinguish itself from siblings such as explain_evidence_mdv.

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?

Provides explicit when-to-use guidance through 适合回答... examples like '取证该从哪开始' and 'K=2 是什么意思'. It lacks when-not-to-use or named alternatives, so it is clear context without 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?

With no annotations present the description carries the full behavioral burden, and it does disclose the safety profile (read-only, no authentication required) plus the critical semantic caveat that results must not be conflated with check_compatibility. It stops short of describing output shape or any rate/limit behavior, but for a zero-parameter read-only query tool this is solid coverage.

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

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

Front-loads the layer tag and the core concept, then what it returns, then usage questions, then behavioral caveats — a sensible ordering. It is information-dense with domain jargon (MDV, axis, evidence direction) but no sentence is 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?

No output schema exists, so the description must at least orient the agent on what comes back, and it does by naming the three kinds of results (zero-contribution rates, zero-marginal directions, bottleneck axis). Combined with the usage framing and the sibling exclusion, it is essentially complete for a no-arg analytic query.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter-related text is needed or missing.

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 names a specific verb+resource (query Marginal Declared Value / MDV) and enumerates exactly what it surfaces: per-axis zero-contribution rates, evidence directions with permanently zero marginal benefit, and the bottleneck axis. It also explicitly distinguishes itself from the sibling check_compatibility, so an agent can route without opening a schema.

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 concrete when-to-use questions ("which axis is cheapest to fill", "does an axis still have evidence value") and an explicit exclusion: "the semantics differ from check_compatibility; they cannot be mixed." That is both positive selection guidance and a named alternative with a boundary condition.

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. It mentions the returned content (metadata fields) and context, but does not explicitly disclose whether this is a safe read-only operation, error behavior, or the exact-match requirement (the latter is in the schema, not the description). The 'verify evidence strength' purpose hints at non-destructive use, but lacks explicit behavioral guarantees.

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, front-loaded with the main action and resource, followed by a concise use-case statement. Every word earns its place; no filler or repetition.

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

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

The tool has a single parameter and no output schema, yet the description covers purpose, return fields, and use context. The schema supplements with matching rules. It lacks an explicit 'not found' behavior or output format, but given the simplicity, it is adequately complete for an agent to select and invoke 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 schema describes the id parameter in detail (exact match, case sensitivity, no fuzzy lookup, suggestion to get from search_components, ID prefix caution). Schema description coverage is 100%, so the baseline is 3. The description itself adds no additional parameter semantics beyond mentioning the ID.

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 '获取' (get) and the resource '单个零部件的完整字段' (complete fields of a single component), distinguishing it from sibling tools like search_components (search) or check_compatibility (compatibility). It also lists specific metadata fields, leaving no ambiguity about its function.

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 a clear use context: '用于在做出采购/设计决策前核对证据强度' (used to verify evidence strength before procurement/design decisions). The schema additionally advises obtaining the ID from search_components, implying a sequential workflow. However, it does not explicitly exclude alternative tools or state when not to use it, so it's not a full 5.

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 transparency burden. It discloses important behavioral context: the database contains many torque/speed variants (19 torque calibers, 37 speed calibers, even Gbps and rad/s mixed in), and the tool returns normalization aids rather than modifying data. It does not state edge cases like failure modes, but it goes well beyond a bare 'return parameter semantics' statement.

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 core purpose, and every clause earns its place: the first sentence establishes the problem (semantic ambiguity), and the second lists the outputs and use case. There is 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 zero-parameter metadata lookup tool, the description is complete: it explains why the tool exists, the data-quality issues it addresses, what it returns, and how to apply the result. Since there is no output schema, the detailed enumeration of return components (physical red lines, unit conversions, comparability grades, vendor inquiry list) is sufficient.

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 the input schema is empty, so the baseline is 4. The description adds context about the domain (torque/speed calibers and unit ambiguity) that helps an agent understand what the tool operates on, even though there are no explicit parameters to document.

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 opens with a specific action ('获取参数口径规范') and clearly identifies the resource (parameter definition norms). It then lists concrete outputs (physical red lines, unit conversion, comparability grading, vendor inquiry checklist) and states the intended use ('判断两份参数表到底能不能直接比较'), which distinguishes it from sibling tools like search_components or recommend_for_application.

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 explicitly states when to use the tool: when determining whether two parameter tables can be directly compared, especially in cross-vendor contexts with ambiguous units. It does not explicitly name sibling tools or state when not to use it, but the context is clear enough for an agent to select it appropriately.

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

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

With no annotations the description carries the full burden and does well: it declares read-only and auth-free operation, and warns that the number is one debatable caliber rather than objective measurement, plus explains the non-obvious gated rule (composed=0 forces the body dimension to 0). It does not describe output shape or any caching/rate behavior, which keeps it from a 5.

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 with what is computed, then usage examples, then the caliber caveat – a logical order with no filler sentences. It is dense but every clause (dimensions, 分子/分母/口径, 门控 vs 朴素) carries information; the repeated 口径 phrasing is the only minor slack.

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 zero-parameter, no-annotation, no-output-schema tool, the description supplies what is returned, how it is computed, the gated-vs-naive distinction, and the read-only/auth-free profile. The one remaining gap is the concrete response shape, which the absence of an output schema leaves to inference.

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

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

The tool takes no parameters, so per the rubric the baseline is 4. Nothing in the description conflicts with the empty 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 resource (核心目标完成度) and exactly what it returns: four-dimension decomposition with numerator/denominator/口径/gap plus weighted completion under two calibers. It is clearly distinct from the compatibility/composition/component siblings, though it never names an alternative, so differentiation is implicit rather than explicit.

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 concrete trigger questions ('这个项目做到什么程度了', '核心目标完成了几成', 'composed 为什么是 0'), which is a clear usage context. It does not state when NOT to use it or point to any sibling tool for adjacent questions, so it stops 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.

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 fully explains the tool's operation: it is an automated cross-validation, read-only in nature (returns results), not a compatibility ruling, and it identifies unverifiable entries and gaps. It also states the intended follow-up (manual evidence completion), providing rich context beyond a simple 'returns audit results'.

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 consists of three sentences, each adding valuable information: what it returns, what it is not, and what it is for. While not as terse as a two-sentence ideal, every sentence earns its place and there is no 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?

For a tool with a single optional parameter and no output schema, the description covers the main output categories (verifiable, unverifiable, gaps, coverage) and clarifies the non-goal (compatibility ruling). It lacks explicit detail about the exact report structure or response format, but this is not critical given the simple parameter and the thorough narrative description.

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 already provides a 100% documented parameter with an enum and default ('scope: all/conflicts'), so the baseline is 3. The description adds no specific parameter-level semantics beyond the overall purpose, but that is acceptable given the schema coverage is complete.

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 cross-validation results between standard registration forms and entity declarations, specifying what it verifies (mechanical/bus declarations) and what it indicates (gaps, coverage). It explicitly distinguishes itself from compatibility checks by stating 'not a compatibility ruling', which separates it from siblings like bom_compatibility_check and check_compatibility.

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 context for use: it is a data quality self-check, not a compatibility ruling, and its purpose is to flag entries with questionable provenance for manual evidence completion. However, it does not explicitly name alternative tools to use instead (e.g., check_compatibility), leaving the when-not-to-use partially implied.

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 behavioral burden. It explicitly states the tool is read-only, requires no authentication, returns a structured JSON report with severity/issues/summary/stats, and lists the exact checks performed. This gives an agent a solid mental model of behavior and side effects.

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

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

The description is compact and information-dense: purpose, return format, check categories, and usage context are all covered in four sentences. Every sentence contributes value, and the core purpose is front-loaded.

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?

Although there is no output schema, the description explains the return structure. It also covers the input domain, the check scope, the read-only/no-auth behavior, and the intended usage scenario. An agent has enough context to select and 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?

Schema description coverage is 100%, so the schema already documents both parameters fully. The description adds no parameter-specific meaning beyond what the schema provides, which matches the baseline of 3 for high schema coverage.

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

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

The description names a specific verb and resource: static compatibility checking of URDF XML files. It enumerates ten concrete check categories, making the tool's scope unmistakable and clearly distinguishing it from the sibling tools, which target BOM/component compatibility rather than URDF files.

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 gives a clear use case: pre-upload compatibility validation for URDF files in RoboParts. It does not explicitly state when not to use this tool or name alternatives, but the resource-specific context is enough to guide an agent away from the component/BOM-focused 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 provided, the description carries the burden. It discloses the heuristic nature and the need to verify against datasheets, which is useful. However, it does not mention fallback behavior (e.g., category listing when no match), price coverage limitations, or read-only characteristics; these are partly covered in the schema but not in the description itself.

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 three sentences long, front-loaded with the main purpose, followed by the return behavior and a necessary caveat. Every sentence adds useful information with no redundancy 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?

No output schema exists, so the description should clarify return details. It mentions per-category candidates and reasons but omits count semantics, scene_matched flag, and price_fit behavior. However, the schema's parameter descriptions compensate for budget and application behavior, making the tool invocable despite the gaps.

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 100%, so the schema fully documents all three parameters. The description only repeats the budget parameter's existence without adding new meaning, and it does not explain count or application semantics beyond what the schema already provides, so the baseline of 3 is appropriate.

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 recommends component combinations by application scenario and returns per-category candidates with reasons. It also characterizes the recommendation as heuristic and non-authoritative, which helps differentiate it from the sibling search_components tool, though it does not explicitly name that alternative.

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 clearly implies use for application-based recommendations and adds a caveat that it is not engineering advice. The application parameter's schema description explicitly directs users to search_components when no matches occur, providing an alternative path, but the main description lacks explicit when-not-to-use guidance.

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 does well: it states read-only and auth-free behavior ('只读、免鉴权'), the same engine as /api/compatibility, the downgrade rule at <2 evidence items, and explicit listing of missing evidence. No annotation contradiction exists.

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?

Four dense sentences with no filler; each clause adds a distinct fact: purpose, engine identity, governor behavior, return contract, and auth. The most important behavioral caveats are front-loaded.

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 2 parameters, no annotations, and no output schema, the description adequately covers safety, return summary, and logic. Minor gap: the four dimensions and evidence-contract structure are named but not detailed, and there is no explicit routing to simpler 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?

Schema coverage is 100% and the schema already documents ID format and the search_components prerequisite. The tool description itself adds no parameter-level detail, so the baseline of 3 is appropriate.

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 opens with a specific action and resource: '对两个零部件做「多 Agent 质保复核」'. It differentiates itself from plain compatibility checks by describing the Worker/Governor layered review and L0–L3 risk grading, making it distinguishable from siblings like check_compatibility and bom_compatibility_check.

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 clearly frames the tool for high-assurance QA review scenarios ('质保复核', 'Governor 层独立复核结论'), so an agent can infer when a deeper audit is wanted. It does not explicitly name sibling alternatives or exclusions, but the context is clear enough for selection.

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, and it delivers thoroughly. It discloses the return format, the 20-category scope, the deliberate non-hardcoding of inventory numbers (pointing the agent to initialize/GET /mcp to avoid copy drift), the substring/non-fuzzy/non-correcting keyword semantics with concrete failure examples, exact-match category behavior with alias pitfalls, and the default exclusion of 3 market-intelligence entries. This is exemplary behavioral transparency that directly prevents agent mistakes.

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 four sentences, front-loaded with purpose before scope and caveats. Every sentence earns its place, including the pragmatic inventory-drift caveat which prevents stale hardcoded numbers. It is appropriately sized for the tool's complexity and does not pad or repeat schema content.

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 4-parameter search tool with no annotations and no output schema, the description is largely complete: purpose, filters, return fields, category scope, and a guidance pointer for inventory. The main gap is the absence of explicit differentiation from semantic_search, a close sibling whose matching behavior could confuse an agent; mentioning when to use each would make this fully 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 coverage is 100% and the schema descriptions are themselves exceptionally rich (concrete examples, matching semantics, alias caveats). Since coverage is high, baseline is 3. The description adds marginal but real value by specifying what the summary return contains and the 20-category coverage, which helps an agent choose keyword/category values. It does not contradict the schema and complements rather than repeats 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 states a specific verb and resource ('搜索机器人零部件' – search robot components), lists the filter dimensions (category, keyword), and specifies the returned summary fields (id/name/category/manufacturer/key specs/evidence level). It is clear, but it does not explicitly name a sibling it is not – notably semantic_search, which is the closest alternative and likely differs on matching semantics. The keyword param's '非模糊' (not fuzzy) hint implies the differentiation without naming it.

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?

Parameter-level usage guidance is excellent: keyword explains substring matching, the disjoint Chinese/English result sets with concrete test data ('六维力' hits 16, 'force torque' hits 2, intersection 0), and the single-word-then-narrow-by-category recommendation ('harmonic drive 20Nm' returns 0, 'harmonic' returns 9). Category explains exact-match semantics and that category does not map 1:1 to ID prefixes. However, there is no tool-selection guidance – the description never says when to prefer this over semantic_search or get_component_detail, so no exclusions/alternatives are stated.

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. It discloses that the semantic index is built offline with precomputed TF-IDF vectors, zero external calls, and zero external models, and that it falls back to keyword search with explicit notification. This is good transparency, though it doesn't detail return format or error handling.

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 and front-loaded, starting with the core purpose and example, then explaining the underlying mechanism and usage guidance. 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 the tool's moderate complexity, the description covers purpose, mechanism, usage guidance, and fallback behavior. It lacks explicit return format details, but since there is no output schema, the description could have mentioned what the response contains (e.g., component IDs, scores). Still, it's fairly complete for a search tool.

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

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

Schema description coverage is 100%, so the schema already documents both parameters well. The description adds context about the k parameter's trade-off (larger k means broader recall but more deviation from intent) and provides example queries for the query parameter, adding value 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 the tool performs semantic recall using natural language queries to return the most similar components. It distinguishes itself from sibling tools like search_components (keyword substring matching) and check_compatibility (compatibility judgment), positioning itself as a 'discovery' channel.

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 explicitly states when to use this tool: when uncertain about exact part numbers or parameter names, semantic search is more robust than keyword substring matching. It also mentions fallback behavior to keyword search when the index is unavailable, providing clear usage context.

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