MCP Midtrans Documentation Server

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

Annotations declare readOnlyHint=true and idempotentHint=true. The description adds valuable behavioral context by detailing exactly what corpora are searched (topics, guides, schemas, examples), which helps the agent understand result breadth. It also describes the return value as 'Matching documentation sections with relevant content', complementing the existing output schema.

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?

Follows a clean docstring structure with summary, scope, usage guidelines, Args, and Returns. Every sentence earns its place: the first sentence defines purpose, the second expands scope, the third gives usage guidance, and the Args/Returns sections are terse. No redundancy or 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?

For a single-parameter search tool with complete annotations (safety hints) and an existing output schema, the description covers all necessary ground: it explains the search scope, return format, and selection criteria. The Returns section acknowledges the string output type without needing to replicate full schema details.

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 Args section states params 'Contains the search query string', which provides minimal semantic meaning beyond the schema. While the schema (via $ref) actually contains rich descriptions and examples for the query parameter, the context signals indicate 0% schema description coverage, suggesting the description should compensate more for parameter structure and constraints (e.g., minLength/maxLength). The description meets baseline but does not richly elaborate.

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 opens with the specific action 'Search' and resource 'Midtrans Core API documentation', then clarifies the scope spanning 'documentation topics, payment method guides, JSON schemas, code examples, and reference materials'. It distinguishes from siblings like midtrans_get_documentation by specifying 'when unsure which topic contains the answer', making it clear this is a broad search vs. specific retrieval.

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?

Provides explicit context for when to use the tool: 'when you need to find specific information across multiple documentation sections or when unsure which topic contains the answer'. This effectively guides selection against more specific retrieval tools. However, it does not explicitly name sibling alternatives (e.g., midtrans_get_documentation) that should be used when the topic is known.

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