Consulta el catálogo curado de Fusión Studio: 38 combinaciones tipográficas y 60 paletas de color, categorizadas por personalidad e industria.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Tipo de catálogo | both |
| limit | No | Máximo resultados por categoría | |
| industry | No | Filtrar por industria: gastronomía, salud, tecnología, retail, etc. | |
| personality | No | Filtrar por personalidad: elegante, moderno, cálido, profesional, etc. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits, but it only states what the catalog contains. It does not mention the read-only nature explicitly, the default limit of 10 results per category, or how filtering by multiple parameters interacts. This leaves significant gaps in understanding the tool's runtime behavior, similar to the update_drive example.
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, information-dense sentence that front-loads the core purpose and key details. It avoids redundancy and fluff, making it an appropriately sized definition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's relative simplicity and the absence of an output schema, the description provides an acceptable overview but lacks clarity on the exact return structure (e.g., list vs. grouped results) and default behavior when no parameters are provided. The mention of 38 typography and 60 palettes could be misconstrued as the total result set, whereas the limit parameter defaults to 10 per category.
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 100% coverage with descriptions for every parameter, so the baseline is 3. The description reinforces that personality and industry are filtering categories, but it does not add significant new meaning beyond the schema's parameter descriptions, which already explain 'Filtrar por industria' and 'Filtrar por personalidad'.
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 purpose with a specific verb ('Consulta') and resource ('el catálogo curado de Fusión Studio'), detailing its contents (38 combinaciones tipográficas y 60 paletas de color) and categorization dimensions (personalidad e industria). This distinguishes it from sibling tools like brand_book_viewer and generate_proposal, which focus on viewing or creating specific brand assets.
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 as a query tool for design catalog content, but it does not explicitly state when to use it over alternatives or provide exclusions. While the purpose makes it clear this is for browsing curated visual options, there is no guidance on scenarios where other sibling tools would be more appropriate, such as when needing to generate a proposal or audit a brand.
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.
Each tool targets a distinct stage of the branding workflow: audit, status, viewing details, proposal, purchase, and catalog. The only potential overlap is between brand_book_status and brand_book_viewer, but their descriptions clearly distinguish progress tracking from full content access.
Tools use snake_case throughout with a mostly predictable pattern, but there is a mix of noun_noun (brand_audit, brand_book_status) and verb_noun (generate_proposal, purchase_brand_book) forms. The style is consistent and readable, though not uniformly verb-first.
Six tools is well-scoped for a niche branding service, covering discovery, sales, and delivery without redundancy or bloat. Each tool earns its place in the workflow.
The core journey from audit to proposal to purchase to accessing the brand book is fully covered, with the visual catalog as a useful resource. Minor gaps like a list-all-brand-books tool or an update tool exist, but they are likely handled outside the agent's scope.