FREE analyzability check before paying for portrait_analysis: is a face detectable, is the photo quality good enough (clipping/color cast)? Deterministic, no LLM. 10/hour/IP.
| Name | Required | Description | Default |
|---|---|---|---|
| image_url | No | ||
| image_base64 | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, but description discloses deterministic behavior (no LLM), rate limiting, and specific checks (face, clipping/color cast). Could add return value details, but provides strong transparency for a read-only check.
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?
Three dense sentences covering purpose, checks, and constraints. Front-loaded with key info, 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?
Describes what the tool checks but omits how to invoke it (parameters) and what the return format is. With no output schema, the description should clarify output, but overall it's understandable for a simple precheck.
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% and description never references image_url or image_base64. Parameter names are self-explanatory but no guidance on which to use or if both are acceptable.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it's a free precheck for portrait_analysis, checking face detection and photo quality. Distinguishes from sibling portrait_analysis by positioning as a preliminary gate.
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 'before paying for portrait_analysis', indicating the intended sequence and alternative. Mentions rate limit 10/hour/IP as a usage constraint.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools have unclear boundaries: document_pipeline and parse_document both parse PDFs, portrait_analysis and style_profile both perform color analysis, enrich_company and jp_company_profile both resolve company profiles, and jp_payroll_suite bundles capabilities that already exist as separate tools. Descriptions are detailed, but an agent must carefully compare several near-synonyms before selecting.
All names are snake_case, but the conventions are mixed: get_* for metadata, jp_* for Japan-specific calculations, pdf_* for PDF operations, plus standalone nouns like meal_vision and style_profile. The prefixes help readability, but there is no uniform verb_noun pattern and ordering is inconsistent (quote_parse vs parse_document).
35 tools is far above the well-scoped 3-15 range and indicates an aggregator/marketplace rather than a focused server. Even with clear individual descriptions, the sheer breadth across OCR, PDF, Japan tax, style, and marketplace functions makes the tool set feel heavy and harder to navigate.
Within its broad marketplace scope, the server is fairly complete: paid products have free samples (get_sample), quotes (quote_parse), receipt retrieval (get_receipt), and discovery via get_catalog and search_x402_services. PDF and Japan tax coverage are extensive, though the wide domain spread means no single area feels fully exhaustive.