get_blocksGets block types: what each does, where it can be used, its outputs, the JSON Schema of its settings and of its result. Get all the types you need in one call.
| Name | Required | Description | Default |
|---|---|---|---|
| types | Yes | The block types, like action_member_ban. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds the substantive detail that each entry includes behavioral info, usage locations, outputs, and settings/result schemas. It omits edge-case behavior such as unknown type names or the 30-item cap's consequences.
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, front-loaded with purpose, and the second sentence adds a non-redundant batching instruction. No filler.
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 no output schema, the description correctly spends its words describing the return payload, which is the main thing an agent needs. Minor gap: no acknowledgment of the 30-type maximum or failure modes for invalid type names.
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% and the single 'types' array is documented with an example value, so the schema carries the load. The description only reinforces plurality ('all the types you need') and adds no format or naming 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?
States a specific verb and resource ('Gets block types') and enumerates exactly what is returned: behavior, allowed locations, outputs, and the JSON Schemas of settings and result. That is far more informative than the sibling list_* tools, though it does not contrast itself with search_blocks, which is the nearest alternative an agent must choose between.
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?
'Get all the types you need in one call' implies batching rather than one type at a time, which is useful steering. However, there is no explicit guidance on when to use this versus search_blocks, or what happens if a requested type does not exist.
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.