Create a new schema in Selise Blocks GraphQL API.
Args: schema_name: Name of the schema to create project_key: Project key (tenant ID). Uses global tenant_id if not provided
Returns: JSON string with schema creation result
| Name | Required | Description | Default |
|---|---|---|---|
| project_key | No | ||
| schema_name | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description must carry the behavioral transparency burden. It does disclose the return format ('JSON string with schema creation result') and the project_key fallback to global tenant_id, but it does not mention whether the schema requires later finalization (via finalize_schema), permissions needed, or other side effects. This is a significant gap given the existence of related siblings.
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 concise: a single-sentence summary followed by a structured Args/Returns block. Every line contributes information, the main action is front-loaded, and there is no redundant or filler 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?
The tool is simple with only 2 parameters and an output schema, so the description doesn't need to explain return details. It covers the core purpose, all parameters, and the return format. However, it lacks lifecycle context (e.g., whether finalize_schema is required afterward) and usage guidance, which prevents it from being fully complete for agent decision-making.
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?
Despite 0% schema description coverage, the description explicitly explains both parameters: schema_name as 'Name of the schema to create' and project_key as 'Project key (tenant ID). Uses global tenant_id if not provided'. This adds real meaning beyond the schema titles, including a default behavior, fully compensating for the schema's lack of 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 first sentence clearly states the action and resource: 'Create a new schema in Selise Blocks GraphQL API.' This is a specific verb+resource statement that distinguishes it as a creation operation. However, it doesn't explicitly differentiate it from sibling tools like finalize_schema or update_schema_fields, so it falls short of a 5.
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 creating schemas, which is a clear context, but it offers no explicit guidance on when to use it versus alternatives or any prerequisites. No exclusion or alternative tool references are provided, so it meets the 'implied usage' level.
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.
The tools are organized into clear domains (auth, roles, schemas, translations, projects), and within each domain, tools have distinct purposes (e.g., get_schema vs list_schemas, save_captcha_config vs update_captcha_status). A few pairs like get_auth_status and get_authentication_config could cause minor confusion, but their descriptions clarify the difference.
All tool names follow a consistent verb_noun pattern in snake_case, using predictable verbs like get, list, create, update, set, enable, and configure. Even longer names like save_module_keys_with_translations adhere to the same convention, with no mixed casing or arbitrary styles.
With 36 tools, the server exceeds the typical well-scoped range for MCP servers. While the broad platform domain justifies some breadth, the sheer volume can overwhelm agents and suggests the toolset could be consolidated or split into smaller, focused servers.
The toolset provides decent coverage for creation, listing, and some updates across entities like permissions, roles, schemas, and translations. However, there are notable gaps: no delete operations for most resources, no role update, and no project update/delete, which leaves lifecycle management incomplete.
