메리츠 기준정보

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

The description clearly discloses dispatcher-style behavior: api_type selects one of five GET endpoints, and api_type='describe' returns parameter explanations. This aligns with the annotations (readOnlyHint, idempotentHint, destructiveHint=false) and adds useful behavioral context beyond the schema, though it omits details like error behavior or rate limits.

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 compact and efficient: two short prose lines plus a clearly aligned five-row table. The routing instruction is front-loaded, and every line contributes useful information without repetition or 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?

For a read-only router with an output schema, the description provides the essential operation list, HTTP verbs, and a self-describe fallback for parameter details. The main gap is the absence of per-endpoint parameter examples, but the describe mode mitigates this and allows an agent to discover the details at runtime.

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?

With 0% schema description coverage, the description partially compensates by explaining that api_type selects the endpoint and params holds parameters, and by pointing to the describe mode for parameter details. However, it does not document the actual parameters for each of the five endpoints, so an agent must call describe to learn the exact parameter names and formats.

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 identifies the resource as reference data and enumerates five concrete GET operations with clear labels (domestic/overseas market days, market hours, and exchanges). It is specific enough to distinguish the tool from trading or account tools, though it does not explicitly contrast it with siblings like meritz_info or meritz_market.

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 explains the routing mechanics: choose an API via api_type and supply params. It does not explicitly state when to use meritz_reference versus alternative sibling tools, but the listed operation names strongly imply it is for static reference lookups such as market days and exchange lists.

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