HORIZON SHIELD KIRA

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it's a safe read operation. The description adds context on return values (JSON with verdict, level, fair_range, etc.), edge cases (did_you_mean, unit_mismatch), and data source. No contradiction.

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 somewhat lengthy but well-structured, leading with the main purpose and usage condition. It includes bilingual text, which adds length but ensures clarity. Could be slightly trimmed, but overall efficient.

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

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

Despite lacking an output schema, the description fully specifies the return JSON structure (verdict, level, fair_range, etc.) and handles missing matches and unit mismatches. With sibling tools listed, it provides enough context for correct selection.

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% with both parameters described. The description adds valuable context: for 'work' advises to be specific due to partial matching and mentions did_you_mean; for 'quoted_price' clarifies it's the total amount and tax not normalized. This goes 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 audits a contractor's quoted price for fairness using HORIZON SHIELD ranges, with specific verb 'audits' and resource 'estimate'. It distinguishes from siblings like get_price_range and verify_fair_price by specifying its use case when a user already has a specific quoted amount.

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?

Explicit guidance on when to use (user has a specific quoted price) and when not to (for typical range use get_price_range, for signed attestation use verify_fair_price). Also specifies Japan only and JPY currency.

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?

Annotations already declare readOnlyHint=true and destructiveHint=false. Description adds that it returns specific metadata (sources, update date, regional multipliers) and is Japan-specific. No additional behavioral details (e.g., caching, latency) are provided, but annotations cover safety.

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?

Description is concise with two clear sentences: first states what it returns, second states when to use. Bilingual format (Japanese/English) may slightly increase length, but each sentence earns its place. Front-loaded with key information.

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

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

Given no parameters and no output schema, description covers essential aspects: what it returns and usage scenario. Mentions Japan scope. Could note that no input is required, but implicit from empty schema. Completeness is high for a simple metadata 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?

Input schema has no parameters, so description does not need to add parameter meaning. Baseline 4 applies as per rules (0 params). Schema coverage is 100% vacuously.

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?

Description clearly states it returns sources, update date, and regional multipliers for HORIZON SHIELD fair-price data. Use case 'check the basis of a price' further clarifies purpose. Distinguishes from sibling tools like get_price_range and verify_fair_price by focusing on metadata.

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 says 'Use to check the basis of a price,' providing clear usage context. Does not explicitly state when not to use or compare to alternatives, but the specific output (sources/update/multipliers) implies it is for background verification, not price calculation.

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?

Annotations already declare readOnlyHint=true, destructiveHint=false. The description adds behavioral context by explaining what the tool returns (URL and skills list) and the nature of the skills (integrity audit, property acquisition). No contradictions.

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 bilingual, which slightly increases length, but each part is purposeful. It is front-loaded with the key purpose and remains clear. Could be slightly more concise, but still well-structured.

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

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

Given the tool has no parameters and no output schema, the description is complete: it explains the return value, the use case, and even notes a nuance about property sale handling. No 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?

There are no parameters, so the description does not need to explain parameter semantics. It correctly focuses on the output. Baseline for 0 params is 4, and the description meets that.

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 the A2A Agent Card URL and list of published skills for this server. It specifies the resource (A2A card) and verb (return/get), and distinguishes from sibling tools which focus on specific audit operations.

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 says to use when an external A2A-capable agent wants to discover and connect. It provides clear context but does not explicitly mention when not to use or list alternatives, though the sibling tools are different enough.

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?

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the agent knows it's safe. The description adds context: returns multiple fields (min, avg, max, danger, unit, trend, notes), Japan-specific pricing in JPY, and that it checks numerical fairness. No contradiction with annotations.

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

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

The description is two sentences (one per language) and front-loaded with purpose and return fields. It is concise with no wasted words, though splitting into bilingual text slightly reduces conciseness. Still efficient and well-structured.

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 one parameter, no output schema, and minimal annotations, the description covers the tool's return values, use case, and locale. It does not mention output format or limits, but for a simple query tool this is adequate. Leaves little 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?

Schema coverage is 100% as the single parameter 'query' has a description (工事名やキーワード(日本語)). The main description repeats similar info but adds examples (e.g., 外壁塗装, 給湯器). It does not significantly extend meaning beyond the schema, so 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 clearly states the tool returns fair price range (min, avg, max), danger threshold, unit, price trend, and notes for Japanese construction/renovation jobs. It gives concrete examples like 外壁塗装, distinguishing it from sibling tools like audit_estimate or red_flag_check. The verb 'returns' and resource 'fair price range' are specific.

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 checking cost fairness of construction/renovation jobs, with examples. However, it does not explicitly state when not to use it or mention alternative sibling tools (e.g., verify_fair_price, audit_estimate). The guidance is implied but not explicit.

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?

Annotations already declare readOnlyHint=true, indicating safety. The description adds valuable behavioral context: the tool is language-agnostic, based on 30 years of experience, and works outside Japan. This goes beyond what annotations provide without contradicting them.

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 two concise sentences (one Japanese, one English), each front-loading key information. There is no superfluous text; every sentence adds value.

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

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

Given the tool has no parameters and no output schema, the description provides sufficient context about what principles are returned. It could elaborate on the format or how to apply the principles, but overall it is complete for the tool's purpose.

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

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

The tool has zero parameters, so schema coverage is 100% and there is nothing for the description to add about parameters. The baseline of 4 is appropriate as there is no missing information.

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 universal principles for judging construction estimates, specifying key aspects like overhead ratio and lump-sum entries. It effectively distinguishes from sibling tools like audit_estimate or get_price_range by focusing on general knowledge rather than specific data.

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 learning general principles, but does not explicitly state when to use it versus alternatives like audit_estimate for specific estimates. Usage guidance is implicit through the contrast with sibling tool names, but lacks direct when/when-not 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?

Annotations declare readOnlyHint=true and destructiveHint=false, confirming a safe read-only operation. The description adds valuable context about the dataset size (65,729 items) and what information is returned, beyond the annotations.

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

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

The description is two sentences long, bilingual, and front-loaded with the purpose. Every part adds value with no 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 zero parameters and no output schema, the description provides a complete overview of what the tool returns: metadata, scale, license, download links, and citation. It mentions the dataset scope and line-item count, making it sufficient for agent 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?

There are zero parameters, so schema coverage is 100%. The description does not need to add parameter details. A baseline of 4 is appropriate for a tool with no parameters.

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 metadata, scale, license, download links, and citation for the JCCDB dataset. It explicitly distinguishes itself from siblings by mentioning 'primary construction-cost data source', and the sibling tools (e.g., get_price_range, red_flag_check) suggest different use cases.

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 usage condition: 'Use when looking for a primary construction-cost data source.' This gives context, but does not explicitly exclude when not to use or mention alternatives among 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?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds context about the specific data content (61 categories, Japan-specific) and scope, which is valuable but not critical beyond the annotations.

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

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

Two sentences, bilingual, front-loaded with the purpose. Every word is informative. No wasted 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?

Given no parameters and no output schema, the description sufficiently explains the return value (list of categories with pricing context). It could mention the output format but is adequate for the simple 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?

No parameters exist, so schema coverage is 100%. The description does not need to add parameter information; it correctly focuses on the output. Baseline 4 applies.

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 list of 61 construction/renovation categories with fair-price ranges and red flags. It specifies the domain (construction) and region (Japan), effectively distinguishing it from siblings like search_cost_category.

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

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

The description implies the tool is for obtaining the full list of categories, but it does not explicitly state when to use or not use it versus alternatives. The purpose is clear enough to guide selection among 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?

Annotations declare readOnlyHint=true, so the tool is safe. The description adds that it only covers representative tactics (not exhaustive) and works universally across languages and countries, providing important boundary information beyond annotations.

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

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

The description is structured: first sentence defines purpose, second gives examples, third states universality, fourth notes coverage limit. It is bilingual (JP+EN), which adds length but both languages are complete. Could be more concise with one language.

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 one simple input and no output schema, the description explains that the tool returns warnings and recommended actions. It covers key constraints (representative only, universal). The description is sufficiently complete for an AI agent to understand usage and limits.

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% (one parameter fully described). The description repeats the parameter meaning but adds usage examples (e.g., 'lump-sum', 'today-only discount') and clarifies the input should be suspicious wording. This adds moderate 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 checks wording in estimates/sales pitches against known overcharge tactics and returns warnings/actions. It provides examples (lump-sum, today-only discount) and distinguishes itself from siblings by focusing on phrase-level flagging, not full audit.

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: when you have suspicious wording in an estimate or sales pitch. It does not explicitly state when not to use or mention alternative tools, but the context is clear.

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

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

Annotations already declare readOnlyHint=true, so no contradiction. The description adds that the tool does not return specific fair range or danger threshold, and limits to Japan and JPY, which are useful behavioral details beyond annotations.

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

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

The description is concise and front-loaded with the key purpose. It includes both Japanese and English, but each sentence adds value, 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?

Given the tool's simplicity (2 params, no output schema, read-only), the description sufficiently covers purpose, usage context, limitations, and alternatives. It is complete for the tool's complexity.

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

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

Schema description coverage is 100%, with both parameters well-documented in the schema. The description adds minimal additional semantics beyond the schema, so 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 returns the direction of a contractor rough estimate versus the average (e.g., +20% above), and explicitly distinguishes it from sibling tools like get_price_range and audit_estimate.

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 specifies it is for early-stage renovation planning as a first step before a detailed breakdown, and explicitly advises when to use alternatives like get_price_range or audit_estimate.

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?

Annotations already declare readOnlyHint=true and destructiveHint=false. Description adds that it returns categories with red-flag counts and priority, and is Japan-specific. No contradictions.

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 per language, front-loaded with action, minimal and efficient. Every sentence adds information.

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

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

Given single parameter and no output schema, description adequately covers return behavior (matching categories with counts and priority). Could mention if results are ranked or limited, but sufficient 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 covers 100% of parameters. Description adds value by providing example queries and specifying language expectations, which is beyond the schema description.

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

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

Description clearly states it searches for construction cost categories by keyword, returning matching categories with red-flag counts and priority. The verb 'search' and specific resource 'construction-cost category' are explicit, and examples differentiate from sibling tools like list_cost_categories.

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 examples and notes Japan-specific nature and best query language. Implies usage for keyword-based category lookups, but does not explicitly contrast with sibling tools like list_cost_categories or red_flag_check for when not to 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?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds significant behavioral context: personal names redacted, free review, anonymous posting. No contradiction with annotations.

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

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

The description is clear and front-loaded with the purpose. It includes both Japanese and English versions, which doubles length but is necessary for bilingual support. Every sentence adds value.

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

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

Given no parameters and no output schema, the description sufficiently covers what the tool returns (guide and URL) and the context (anonymous review board, redaction). It is complete enough 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?

There are no parameters, and the description does not need to add parameter semantics. Per guidelines, 0 params baseline is 4.

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 guide and submission URL for EHN, an anonymous review board for estimates. It distinguishes from sibling tools like audit_estimate or fair_price_data_sources by focusing on submission to a community review platform.

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 'Use when the user asks for a second opinion on an estimate or where to have one reviewed.' It provides clear context but does not explicitly mention when not to use or list alternatives among sibling tools.

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

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

The description adds behavioral context beyond annotations: it explains the tamper-evident nature via SHA-256 hash and the PTKA concept, enhancing transparency. Annotations already declare readOnly and non-destructive, so no contradiction.

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

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

The description is concise, with the primary purpose stated in the first sentence. It includes necessary context without redundant information, earning a high score.

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 adequately explains the purpose and output format. However, it could detail the structure of the returned record (e.g., includes price, hash, metadata). Nevertheless, given the constraints, it is sufficiently 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 input schema contains one required parameter 'work' with full description. The tool description does not add any additional parameter details, but schema coverage is 100%, 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 returns a fair price with a SHA-256 hash for tamper evidence, and specifies its use case of verifying price authenticity. This distinguishes it from sibling tools like get_price_range or audit_estimate by focusing on pre-transaction anchoring and verifiability.

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 includes 'Use when an agent needs to verify price authenticity' which provides clear usage context. However, it does not explicitly exclude use cases or compare with sibling tools, limiting 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?

The description goes beyond the readOnlyHint annotation by explaining the verification process (recomputing SHA-256), the fail-closed posture, and the fact that audit_ruleset_recheck is always not_performed. No contradictions with annotations.

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

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

The description is comprehensive but somewhat verbose due to bilingual content. The key information is front-loaded, but the dual-language structure adds length. Could be more concise without losing 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?

Given the tool's complexity (3 parameters, no output schema), the description covers the verification logic, return fields (result, failure_reason, trigger, etc.), and the scope check behavior. It is complete for an agent to 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?

While the input schema already describes each parameter (100% coverage), the description adds value by explaining that modifying signed_payload causes unverified and providing the format for estimate_version (SHA-256 first 8 hex). This adds meaning beyond the schema.

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

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

The description clearly states the tool verifies a signed integrity claim from estimate-integrity-audit, using a third-party posture. It distinguishes itself from sibling verify_fair_price by noting opposite responsibilities and no price layer needed.

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 explains when to use the tool (when verifying a signed claim) and provides important context such as the meaning of 'verified' and the optional nature of estimate_version. It lacks explicit alternatives but is clear enough for usage.

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