HORIZON SHIELD WebMCP Intake

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

No annotations are provided, so the description fully covers behavior: it generates drafts, includes backlinks, uses only verifiable first-party prices, does not auto-post, and requires operator finalization. It does not mention rate limits or auth, but for a content generation tool these are less critical.

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 but each sentence adds meaningful information: purpose, content rules, and constraints. It is front-loaded with the main function. Could be slightly more concise by removing redundancy between Japanese and English, but overall structured well.

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 one parameter, no output schema, and no annotations, the description adequately explains the tool's behavior and constraints. It clarifies what the tool does and does not do. The return format is implied (text drafts) but not explicitly detailed, which is acceptable for a simple generation 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 100% with a parameter 'work' described as 'construction name or keyword'. The description adds context that it is for 'construction overcharge warnings' and expects Japanese input, providing examples like '外壁塗装'. This adds meaning beyond the schema definition.

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 generates broadcast drafts with backlinks to HORIZON SHIELD pages, using verifiable first-party prices. The verb 'generates' and resource 'broadcast drafts' are specific. It distinguishes from siblings (intake_estimate, orchestrate, scan_tactics) by focusing on content creation rather than analysis or orchestration.

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 implicitly defines when to use the tool (when needing a draft for construction overcharge warnings) and what it does not do (no auto-posting, operator finalizes). It lacks explicit comparison to sibling tools but the context makes the usage clear.

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

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

No annotations are provided, so the description carries the burden. It describes the tool as an intake desk that bridges to an audit and returns a verdict/check path, but it does not disclose side effects (e.g., data storage) or behavior on invalid input. Adequate but could be more explicit.

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

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

The description is two sentences, bilingual, and front-loaded with essential information. No wasted words; 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?

For a simple intake tool with no output schema and full parameter coverage, the description adequately explains inputs and outputs (verdict and free check path). Minor gap: could detail the verdict format, but overall complete.

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

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

Schema coverage is 100% for both parameters, and the description mostly restates the schema (e.g., '工事名(日本語)' matches schema). It adds an example for 'work' but no additional semantic guidance 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 explicitly states it receives construction quotes and bridges to a fair-price audit, returning a verdict and free third-party check. It uses specific verbs (receives, bridges, returns) and is clearly distinct from sibling tools like draft_broadcast or orchestrate.

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

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

The description clearly implies when to use: when a homeowner has a quote to evaluate. It states inputs (work name and quoted price) and outputs (verdict and free check path). However, it does not explicitly state when not to use or mention alternatives, though siblings are unrelated.

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

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

With no annotations, the description carries full burden. It discloses that the tool performs internal sequential execution, returns bundled results, only uses verifiable first-party prices, and drafts without auto-posting. This adds significant behavioral context beyond just the name and schema.

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 provided in both Japanese and English, making it slightly redundant but still concise. It conveys all necessary information in two sentences per language without unnecessary words or repetition of schema details.

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

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

Given the tool's complexity (orchestrating multiple steps) and the lack of an output schema, the description could be more complete. It states that results are bundled but does not describe the format or error handling. For an orchestrator, this is acceptable but not fully comprehensive.

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%, so baseline is 3. The description adds value by clarifying that 'quoted_price' triggers a KIRA audit, which is not evident from the schema alone. This extra semantic information helps the agent understand conditional behavior.

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

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

The description clearly states it is a one-call orchestrator that runs three distinct sub-tools (intake, scan_tactics, draft_broadcast) in sequence and returns a bundled result. It distinguishes itself from sibling tools which are the individual steps, making the purpose specific and non-ambiguous.

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 (to run the entire pipeline in one call), but it does not provide explicit guidance on when not to use it or alternatives. The sibling tools are listed, implying alternatives, but there is no direct comparison or exclusion criteria.

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

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

With no annotations, the description carries full burden. It discloses that the tool returns verified data, points to sources, does not infer new cases, and is for awareness not price judgment. This provides good behavioral context beyond the schema.

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

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

The description is concise with two sentences in English and a parallel Japanese version. Front-loaded with purpose, every sentence adds value. No redundancy beyond bilingual necessity.

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 annotations, no output schema, and a single parameter, the description is complete. It explains the source, expected input, what is returned, limitations, and agent responsibility. Adequate for correct usage.

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% for the single parameter 'work', with a clear description. The tool description adds minimal value beyond stating it takes a job name/keyword, not adding syntax or constraints. 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 uses specific verbs ('returns', 'points') and clearly identifies the resource (verified overcharge tactics from HORIZON SHIELD). It distinguishes itself from sibling tools by focusing on overcharge tactics with verification, not pricing or estimation.

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 (for overcharge tactics on a job/keyword) and what not to rely on (not a price verdict, not for new cases). It instructs the calling agent to read primary sources for the latest cases, but does not explicitly mention when not to use or compare to sibling tools.

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