MCP Midtrans Documentation Server

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

Annotations indicate readOnlyHint=true and idempotentHint=true. The description adds value by specifying the return format ('field table, example JSON, and usage notes') and listing all available object types, which helps the agent understand the scope of valid inputs. However, it does not mention caching behavior or whether this retrieves static reference data versus dynamic schemas.

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 front-loaded with purpose but spends significant space listing 17 object types that are already defined in the schema enum. The Args/Returns structure is clear but somewhat formal. The object list, while helpful for LLM context window visibility, creates redundancy that could be trimmed to improve conciseness.

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 presence of annotations (covering safety/idempotency) and the context signal indicating an output schema exists, the description adequately covers what the tool returns (detailed schema with field tables and examples) and what inputs it accepts. For a documentation reference tool of moderate complexity, this is sufficient without over-specifying.

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 schema has 0% description coverage at the root properties level (per context signal), though the $ref target (object_type) is well-documented in the schema itself. The description compensates by documenting the 'params' wrapper as 'Contains the object type to get schema for' and enumerating all 17 valid object_type values, though it adds no semantic detail beyond the names.

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 'Get[s] the detailed JSON object schema for Midtrans API request/response objects' with specific details about what it includes (field definitions, types, examples). It distinguishes itself from siblings like midtrans_get_code_example or midtrans_get_charge_example by focusing specifically on 'schema' and 'field definitions' rather than examples or general documentation.

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?

While the description lists the 17 available object types that can be queried, it provides no explicit guidance on when to use this tool versus siblings like midtrans_get_charge_example (full request examples) or midtrans_search_documentation (general doc search). It should explicitly state this is for understanding object structure when constructing API requests.

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