device-house

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

Without annotations, the description carries the full burden. It discloses that unrouted connections are treated as failed ('未配線はfailed'), which is a useful behavioral trait. However, it omits other important details such as whether the operation modifies the design or requires specific permissions.

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 leads with the main action. However, the parenthetical '盛らない=未配線はfailed' is slightly cryptic and could be clearer.

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 no annotations or output schema, and the description does not explain the prompt parameter or the exact return format. While it mentions the failure condition, it is incomplete for an agent to invoke correctly without ambiguity.

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 only parameter 'prompt' has no schema description (0% coverage), and the tool description does not explain what the prompt should contain. This leaves the parameter's meaning ambiguous.

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 actual routing with a 2-layer autorouter and returns a summary of wiring rate and via count. It uses a specific verb and resource but does not explicitly differentiate from sibling 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 intended use (routing a PCB) is implied from the description, but no explicit guidance is given about when to use this tool versus alternatives or any 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 present, so the description carries the full burden. It discloses a key behavioral trademark: it separates design-controllable metrics (judged) from real-world tests/applications (marked as '要対応') and explicitly promises honesty ('盛らない'). This tells the agent what to expect in terms of output nuance, though it does not mention side effects or return format.

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 dense sentences pack the purpose, scope, and behavioral policy without redundancy. Key information is front-loaded: '機械チェック' leads, then certifications, then the honesty clause. No filler 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?

Given the low complexity (1 required param, no output schema, no annotations), the description is largely complete: it explains the input type, what is checked, and the honesty policy. The only gap is an explicit description of the return value or output format, but that is not critical for a check tool of 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?

The schema already covers 100% of parameters with a description ('評価したいデバイスを言葉で'). The tool description adds semantic context by linking '言葉から設計したデバイス' to the prompt parameter, clarifying that the prompt should be the verbal device description. This goes beyond the bare schema and helps the agent construct meaningful 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 names a specific action ('機械チェック') and a specific resource ('デバイスの規制適合'), listing concrete certification standards (技適/PSE/CE/FCC/RoHS) and supply-chain aspects (発注先+部品調達). This clearly distinguishes it from siblings like eval_device or manufacturing_readiness, which likely focus on other evaluation or production-readiness aspects.

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

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

The description implies when to use the tool: when you have a device designed from a text description and need a compliance check. It also states the scope (regulatory certifications + ordering + parts) without naming alternatives or exclusions. While not explicit about comparing to siblings, the context is clear enough for an agent to decide.

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 the five evaluation axes, which is helpful context, but it does not explain whether the tool is read-only, what the output format is, or any side effects. For a scoring tool, the lack of return value details is a significant gap.

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

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

The description is a single, concise sentence that front-loads the main action and includes the five evaluation axes. Every part contributes to understanding the tool's purpose with no 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?

The tool has one parameter, no output schema, and no annotations. While the description names the evaluation criteria, it fails to explain the output structure, how scores are presented, or any prerequisites (e.g., whether a device must already be generated). Given these gaps, the description is not sufficient for an agent to fully understand the tool's behavior.

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 shows a single 'prompt' string parameter with no description, so schema coverage is 0%. The description implies that 'prompt' is the natural-language description from which the device is designed, adding some meaning beyond the schema. However, it does not explicitly specify the expected format or content of the prompt, leaving room for ambiguity.

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

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

The description clearly states the tool's function: scoring the generation quality of a device designed from words on five specified axes. It uses a specific verb (scores) and resource (generation quality of a device), distinguishing it from sibling tools like generate_device or compliance_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?

The description implies that the tool should be used to evaluate device generation quality, but it does not explicitly state when to use it versus alternatives, nor does it mention exclusions or when not to use. There is no reference to sibling tools like manufacturing_readiness or compliance_check.

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. It does disclose that actual payment is gated by a human, which is useful, but it does not explain what the tool actually does (e.g., whether it uploads, generates files, or only prepares data). The phrase '盛らない' is vague and without context.

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 short, but it sacrifices clarity for brevity. The mixed Japanese phrases ('盛らない', '人間ゲート') are not self-explanatory and could confuse an agent. A clear, structured explanation would be more effective than this cryptic style.

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 an ordering package (Gerber, BOM, CPL, procedures) and the absence of annotations or output schema, the description is severely underwhelming. It fails to explain key details like file formats, upload behavior, payment flow, or parameter usage, leaving the agent with only a vague hint.

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 description provides no information about the 'qty' and 'prompt' parameters. The agent is left entirely uninformed about what these parameters mean, expected formats, or their roles. There is no compensation for the missing schema descriptions.

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 lacks a clear verb and resource. It says 'Order package summary' and mentions JLCPCB upload/payment, but it's ambiguous whether the tool generates, uploads, or summarizes the package. The phrase '盛らない=実支払いは人間ゲート' is cryptic and doesn't clarify the primary 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?

No explicit guidance on when to use this tool versus alternatives. The mention of 'human gate' hints at a workflow but fails to specify when a user should invoke this tool or what prerequisites exist. No alternatives are referenced.

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 reveals the expected outputs (BoM, enclosure, price, score) but does not state whether the operation modifies state, requires permissions, or has side effects. This is a useful but incomplete transparency.

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

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

The description is a single, compact sentence that front-loads the action and lists the key outputs. Every word contributes essential information without unnecessary elaboration.

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 the core functionality and lists the return outputs, which is important because no output schema exists. However, it leaves some ambiguity around terms like '全軸スコア' and the format of the returned data, but for a single-parameter tool, this is largely 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 single parameter 'prompt' is fully described in the schema with an example ('焚き火に声で参加できる音声デバイス'), providing high schema coverage. The tool description does not add extra parameter semantics beyond what the schema already offers, so the baseline score 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's function: designing a device from a textual use case and returning BoM, enclosure, price, and full-axis score. It uses a specific verb 'design' and names concrete outputs, distinguishing it from sibling tools focused on parts management, compliance, and manufacturing.

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 generating a new device from a user's expressed use case, but it does not explicitly state when to use this tool versus alternatives like eval_device or compliance_check. No direct alternatives or exclusions are mentioned.

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

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

No annotations are present, so the description carries the full burden. It does disclose a meaningful behavioral trait: LCSC numbers are unverified and left blank, which is important for users. However, it does not mention side effects, errors, or any other behavioral constraints beyond that.

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, focused sentence that efficiently conveys the output format and a critical caveat. Every word earns its place, with no redundancy or unnecessary detail.

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, but the description is incomplete: it never explains the 'prompt' parameter, provides no usage context, and lacks an output schema. The caveat about LCSC numbers is useful, but the missing parameter semantics and usage guidance prevent the description from being complete for an 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 only parameter, 'prompt', has no schema description and the schema coverage is 0%. The description does not explain what the prompt should contain, how it relates to the BOM CSV, or any format/constraints. The agent cannot correctly determine how to populate this parameter.

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

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

The description clearly states that the tool returns a BOM CSV in JLCPCB format with specific columns (Comment, Designator, Footprint, LCSC). This is a specific verb+resource+scope and distinguishes it from sibling tools like get_netlist and get_placement.

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 given on when to use this tool versus alternatives. It does not mention prerequisites, typical scenarios, or when another tool (e.g., get_netlist) would be more appropriate. The JLCPCB-specific format is the only implicit hint.

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?

There are no annotations, so the description must convey all behavioral context. It only says 'returns' a template, without disclosing whether it generates dynamically, what side effects (if any) occur, or what the response format is. This is a significant gap for an agent deciding whether to call it.

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 one concise sentence that immediately states the tool's core function. No filler or redundant content; it is well-structured and 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?

With no annotations and no output schema, the description is the only resource. It lacks details about the exact output representation (file content vs. path), required input format, and any dependency on previously designed devices. For a tool with a single prompt parameter, this is insufficient.

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

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

The single parameter 'prompt' has no schema description (0% coverage), so the description must compensate. The mention of '言葉から設計した' implies prompt is a natural-language description of the device, which adds some meaning, but it does not specify expected language, length, or examples.

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

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

The description states the tool returns an Arduino firmware template (.ino) for a device designed from natural language, using a clear verb ('返す') and resource ('Arduinoファーム雛形'). However, it does not explicitly distinguish itself from sibling tools like generate_device, and the phrase '言葉から設計した' is slightly indirect about the prompt-based generation.

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 information is provided about when to use this tool versus the many sibling get_* tools (e.g., get_netlist, get_bom_csv). It does not mention prerequisites, such as whether a device must already be designed, nor suggest alternatives.

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

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

With no annotations provided, the description carries the burden of behavioral disclosure. It adds context about the output being verified for footprint assignment, wiring, and DRC, which signals production readiness. However, it does not explain side effects, permissions, or error behavior, leaving some behavioral aspects undisclosed.

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. The second clause adds relevant context about verification. It is suitably concise with no wasted words, though it could benefit from a slight structural separation of purpose and context.

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 being a low-complexity tool, the description omits critical details: what the 'prompt' parameter should contain, how the output is delivered, and the exact meaning of 'verified' in this context. The absence of an output schema increases the need for description to cover return behavior, but it does not.

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 a single parameter 'prompt' with no description (0% schema coverage), and the tool description does not mention the prompt parameter at all. The agent receives no guidance on what to put in 'prompt', making this parameter completely opaque.

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 a specific verb '出力' (output) and resource 'KiCadネットリスト(.net)', clearly stating what the tool produces. It also distinguishes itself from the sibling 'get_netlist' by specifying the KiCad format and .net extension, making the purpose 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 implies the intended context ('量産正規ルート' = mass-production official route) but does not explicitly state when to use this tool instead of alternatives like get_netlist. The guidance is implied through the verification claim rather than directly 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, and the description only says 'returns' without disclosing any behavioral traits such as side effects, permissions, or format details. It does not add value beyond the basic function, leaving the agent without insight into read-only nature or potential constraints.

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 in Japanese, front-loaded with the core purpose and no unnecessary words. It is appropriately minimal for the simple resources it describes.

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 lack of annotations, output schema, and parameter documentation, the description is insufficient for an agent to invoke the tool correctly. It omits the meaning of 'prompt', the expected return format, and whether there are any prerequisites or alternatives, making the tool under-specified.

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 only parameter 'prompt' has no schema description and the tool description does not explain its meaning or expected format. With 0% schema coverage and no compensation in the description, the agent cannot determine what to pass.

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 wiring netlist and explicitly identifies it as input for autoroute, distinguishing it from sibling tools like get_kicad_netlist. The verb '返す' (returns) and resource '配線ネットリスト' (wiring netlist) are specific and unambiguous.

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

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

The description provides clear context: this netlist is the input for autoroute, implying it should be used when preparing data for autorouting. However, it does not explicitly mention alternatives or when not to use this tool, so it lacks 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, the description carries the burden of explaining behavior. It details the output format (SVG) and the legend for layers/pads/unrouted traces, which is valuable operational context. However, it does not explicitly state that the operation is read-only or mention any prerequisites beyond the PCB being routed.

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 main purpose and encodes the color legend in parentheses. Every element is necessary, with no redundant or filler 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?

The tool has one parameter, no annotations, and no output schema, so the description should explain both input and output to be complete. While the output is thoroughly described, the complete absence of guidance on the 'prompt' parameter leaves a critical gap in usability.

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 only parameter 'prompt' is completely unexplained in both the schema (0% coverage) and the description. The name is generic and gives no hint about expected content, format, or purpose, making it impossible for an agent to know what to provide.

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 2-layer preview of the routed PCB in SVG format, with explicit color mapping (red=top, blue=bottom, gold=pads, dotted=unrouted). The verb '返す' (returns) and the reference to SVG preview distinguish it from sibling tools like get_netlist or get_placement.

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 this tool is used when a visual SVG preview of a routed PCB is needed, but it does not explicitly state when to use it versus alternatives or provide exclusions. There is no mention of other tools for different data formats, so usage context is only 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It merely states the return value without explaining how the CPL CSV is produced, whether it depends on project state, or whether it is purely a read operation.

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

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

The description is a single sentence with no filler, so it is concise. However, it lacks structural elements like parameter documentation or usage examples, making it under-specified for the tool's needs.

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 one parameter, no output schema, and no annotations, the description is incomplete. It does not explain the purpose of the prompt parameter, the expected response format, or how this tool fits into the broader workflow.

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 one parameter, 'prompt', with 0% description coverage, and the tool description does not mention it at all. The agent has no information about what value to provide, making the parameter effectively undocumented.

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

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

The description states it returns the JLCPCB component placement (CPL CSV), which is a specific verb and resource. This clearly distinguishes it from sibling tools like get_bom_csv and get_pcb_svg, which return different artifacts.

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

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

No guidance is provided on when to use this tool versus alternatives. It does not mention any prerequisites, context, or scenarios where this tool should be preferred over similar export 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?

While annotations are absent, the description only states what the tool lists. It does not disclose any behavioral traits such as pagination, output format, sorting, or whether it returns a full list. For a listing tool with no schema, this leaves the agent uninformed about runtime behavior.

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

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

The description is a single concise sentence that conveys the core purpose without any extraneous words. It is well-structured and front-loaded, providing immediate clarity.

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 tool with no output schema, the description is minimally adequate: it states the resource and action. However, it does not explain what an 'archetype' is in this context or what the returned list contains (e.g., names, objects), which would help an agent use the result effectively.

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 schema is empty. With no parameters to describe, the baseline is 4. The description adds no parameter information, but that is acceptable since there are none.

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 'device.houseが言葉から設計できるデバイス種別の一覧' clearly states it lists device types ('デバイス種別') that can be designed from words in device.house. This is a specific verb+resource combination, distinguishing it from sibling tools like parts_list or list_catalog.

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 about when to use this tool versus alternatives such as list_catalog or parts_list. The description gives no context about scenarios or exclusions, leaving the agent to infer usage solely from the tool 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 provided, the description carries the burden of describing behavior. It discloses the output fields (price, dimensions, recommended room, deep link) and implies the tool is read-only by nature, but it doesn't explicitly state that it returns a list, how filtering works, or any side effects. The description adds some context but lacks full transparency.

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

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

The description is a single, compact sentence that includes both the purpose and the key output attributes. There is no wasted language, and it is front-loaded with the main concept ('device catalog'). It is appropriately concise for a simple list 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 tool's simplicity (one optional parameter, no output schema, no annotations), the description provides enough context for an agent to select and invoke it correctly: it identifies the resource, its content fields, and the use case. It doesn't explain return format or edge cases, but for a straightforward catalog listing, this 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 schema description covers 100% of the parameter (room) with an explanation of filtering by recommended room. The description does not add any additional meaning beyond the schema; it only mentions 'recommended room' as an output field, not as a parameter. Baseline of 3 is appropriate since 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 clearly identifies the tool as a device catalog with specific content fields (price, dimensions, recommended room, deep link) and its use case (for placing in house rooms). It lacks an explicit verb like 'list' or 'get', but the name and context make the purpose clear. It doesn't explicitly differentiate from sibling tools like list_archetypes or parts_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 a use case ('for bim.house etc. to place in rooms'), which implies when to use it. However, it doesn't explicitly state when not to use it or mention alternatives among the sibling tools. The guidance is implied through the stated use case rather than explicit instructions.

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

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

With no annotations provided, the description must carry the full burden. It mentions 'honest physical assessment' but does not disclose whether the operation is read-only, whether it modifies objects, or what the output/return format is. This is insufficient for a tool that could be a mutating or analysis operation.

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 brief and front-loaded with the key concept. It does not waste words, but it is terse to the point of omitting necessary details. Still, for what it includes, it is well-structured and easy to scan.

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

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

Given the tool's likely complexity and the absence of annotations, output schema, or parameter explanations, the description is incomplete. It does not explain what the prompt should contain, what results to expect, or how this readiness check fits into the broader design/manufacturing workflow.

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 only parameter is 'prompt', but the description does not mention it or explain what should be placed in the prompt. With 0% schema description coverage, the agent has no idea how to construct a valid request.

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 assesses manufacturing readiness by checking physical footprints, LCSC parts, DRC, fits, and wiring. It implies a verification/assessment action and distinguishes itself from sibling tools like compliance_check by emphasizing 'honest physical assessment' for ordering.

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 given on when to use this tool vs. alternatives such as compliance_check or fab_order_package. It does not mention prerequisites, exclusions, or a recommended workflow.

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 discloses that the operation persists to the user catalog and that the id is optional, with a slug generated from the part number. Lacking annotations, it partially carries the burden of explaining side effects, but omits permissions, error behavior, or duplicate 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 entire description is one concise sentence with two informative clauses. Every word earns its place, making it efficient and front-loaded with no 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?

With nine parameters, no output schema, and no annotations, the one-sentence description is insufficient. It only addresses id and part, leaving the majority of the input structure and expected behavior undefined 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?

Schema description coverage is only 11%, with only 'part' documented. The description adds meaning to 'id' (optional, slug generation) but leaves the other seven parameters (cat, src, desc, unit, keywords, footprint, interface) unexplained, failing to compensate for the low 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 clearly states 'Add parts' with persistence in the user catalog, specifying a verb and resource. It distinguishes from sibling tools like parts_update and parts_remove by the add action, though it doesn't explicitly contrast them.

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 like parts_update or parts_remove. The intended use is only implied by the tool name and the brief phrase 'user catalog'.

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 carry the full burden of behavioral transparency. It only states 'get one part by id' without disclosing whether this is a read-only operation, what happens if the id does not exist, or what the return structure is. This is minimal disclosure for a simple retrieval 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 a single, short sentence that immediately conveys the essential action and parameter. It is front-loaded and contains no filler words. Perfectly sized for the simplicity 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?

With no output schema and no annotations, the description should explain return behavior and error handling. It provides none of that. For a tool with only one parameter and a clear 'get' action, some context about the response or missing-id behavior is still expected, but the description is too sparse to be 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?

The schema has one parameter 'id' with type string and no description (schema coverage 0%). The description adds meaning by stating 'id で' (by id), clarifying that the id is the lookup key. However, it does not provide format, examples, or constraints, so it only partially compensates for the schema's lack of detail.

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 'id でパーツ1件取得' translates to 'Get one part by id', which is a specific verb (get) plus resource (part) plus scope (single item by id). This clearly distinguishes it from sibling tools like parts_list and parts_search, which handle multiple or search-based retrieval.

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

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

The description does not explicitly state when to use this tool versus alternatives. Usage is implied: use it when you have a specific id and need a single part. However, no exclusions or alternative tool names are mentioned, so the guidance is only implicit.

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 but offers only that the list can be filtered by category/interface. It does not disclose return format, pagination, or any side effects, leaving the agent without necessary behavioral context.

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 phrase that conveys the core functionality with no filler words. It is appropriately sized but could benefit from a bit more structure, such as a separate sentence for usage guidance.

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 output schema and sparse annotations, the description leaves many unanswered questions: does it return full part details or summaries? Are there limits? How do the filters behave? The minimal text is insufficient for a complete understanding.

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

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

The description explicitly maps 'cat' to 分類 (category) and 'interface' to インターフェイス, clarifying the bare parameter names in the schema. However, it does not explain the enum values for interface or how filters combine, so it only partially compensates for the 0% schema description 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 clearly indicates the tool provides a list of parts with filter options for category and interface, distinguishing it from part-specific operations like parts_get or parts_search. However, it lacks an explicit verb like 'list' and could more clearly define its return scope.

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 parts_search or parts_get. It only mentions filterability, which does not help the agent choose between related list operations.

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 discloses a non-obvious behavior: built-in parts are not permanently deleted but tombstoned and can be restored by re-adding. This is valuable since no annotations are present. However, it does not clarify whether non-built-in parts are hard-deleted, leaving a small gap.

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

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

The description is a single, front-loaded sentence that efficiently conveys both the primary action and an important edge case. Every word serves a purpose, 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 simple tool with one parameter and no output schema, the description covers the essential behavior and a key special case. It could be more complete by explicitly stating the behavior for custom parts, but it is largely sufficient for an agent to use 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?

With only one parameter 'id' and 0% schema description coverage, the description does not elaborate on the parameter's meaning or format. Although it is likely the part ID, the description fails to compensate for the lack of schema documentation, making this a clear gap.

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

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

The description clearly states 'delete a part' with a specific verb and resource. The parenthetical about tombstone for built-in parts adds important scope clarification, distinguishing it from other part-related tools. It directly addresses the action and its variant for built-in parts.

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?

While the tool is obviously the removal counterpart to parts_add/update, there is no explicit guidance on when to use it vs alternatives or any exclusions. The usage is implied by the name and siblings, but the description does not provide explicit context.

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

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

No annotations are provided, so the description must convey behavioral traits. 'Keyword search' implies a read-only operation, and listing searchable fields adds context. However, it does not explicitly state that no data is modified, nor does it mention result format, pagination, or authorization requirements, leaving moderate 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 a single, concise sentence that front-loads the verb ('パーツをキーワード検索') and immediately states the core function. Every word contributes value, with no filler 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 the low complexity (one simple parameter, no output schema, no annotations), the description provides sufficient context for operation selection: it identifies the tool, its input semantics, and its scope. It could be improved by mentioning the return format or limit behavior, but the description is complete enough for a basic 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 coverage is 0%, so the description must explain the 'query' parameter. It does so by specifying that the keyword applies to part number, description, and usage (型番/説明/用途), adding meaningful semantics beyond the bare 'string' type. Though it does not mention syntax or case sensitivity, it compensates adequately for a single parameter.

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

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

The description clearly states a specific action ('パーツをキーワード検索' = keyword search parts) and the resource (parts), with the searched fields explicitly listed (型番/説明/用途). This distinguishes it from sibling tools like parts_list (which likely enumerates all parts) and parts_get (retrieves a specific part).

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 keyword-based searching but does not provide explicit when-to-use guidance or compare with alternatives like parts_list. There is no exclusion or mention of when not to use it, so it earns an 'implied usage' score.

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 of disclosing behavior. It states the tool returns aggregated statistics (total count and category breakdown), which is useful. However, it does not explicitly mention that the operation is read-only or describe any potential caveats such as data freshness or access requirements.

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 phrase in Japanese, front-loading the key information (overview, total count, by category). There is no redundancy or wasted 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?

Given there are no parameters and no output schema, the description adequately explains what the tool returns (total count and category breakdown). It is complete for a simple stats tool, though it could be slightly more explicit about the exact format or scope (e.g., whether it includes all parts or only certain categories).

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, so the input schema is empty. The description naturally does not need to explain parameter semantics, and the baseline of 4 applies as there is no parameter information to provide.

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 identifies the tool's resource (parts catalog) and its output: an overview including total count and breakdown by category. This distinguishes it from sibling tools like parts_list or parts_search, which likely return individual records. However, it lacks an explicit verb like 'get' or 'retrieve', making it slightly less clear as an action.

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 a high-level summary of the parts catalog is needed, as opposed to viewing or searching for specific parts. However, it does not explicitly state when to use this tool over alternatives, nor does it mention any exclusions or prerequisites.

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 carry the full burden. It mentions '上書き' (overwrite), hinting at destructive behavior, but does not clarify whether it's a partial update, what happens to unspecified fields, authentication needs, or side effects. This is insufficient for a mutation 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 a single, front-loaded sentence that efficiently conveys the core action without unnecessary elaboration. It is concise and to the point.

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 nested patch object, the absence of annotations, and zero parameter documentation, the description is too sparse to fully inform an agent about the tool's behavior, field semantics, and possible outcomes. It covers the basic action but leaves significant 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?

The description references 'price/procurement source' (価格/調達先) which maps to 'unit' and 'src' in the patch object, but it does not explain other fields such as cat, desc, part, keywords, footprint, or interface. Since schema coverage is 0%, the description fails to compensate for the lack of parameter documentation.

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

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

The description clearly states 'update existing parts' (既存パーツを更新) and adds that it can overwrite prices/procurement sources of embedded parts. This is a specific verb+resource combination that distinguishes it from sibling tools like parts_add or parts_remove.

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 updating existing parts but does not explicitly state when to use it versus alternatives like parts_add. It mentions overwriting embedded parts, which gives context, but lacks explicit exclusions or alternative tool references.

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