search_db

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

No annotations are present, so the description carries full burden. It reveals that collection codes are specific (MO, BT, etc.) and that fields can be in Korean or code. It also mentions that results contain data_id for further calls. However, it does not disclose pagination behavior (limit/start), error cases, or if the search is read-only.

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 concise, with one introductory sentence and parameter details in a clear list format. It front-loads the purpose. Minor improvement: could be more structured with explicit labels for each parameter.

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 no output schema, the description should explain return values beyond mentioning data_id. It lacks details on the structure of search results, how pagination works via limit/start, and what happens when no results are found. The tool has 5 parameters and is relatively complex, so more contextual information is needed.

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 description coverage is 0%, so the description must compensate. It adds meaning for collection (lists valid codes and references list_collections) and field (provides both Korean and code options). However, it does not explain query, limit, or start parameters, leaving those ambiguous.

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 starts with a clear statement '특정 컬렉션에서 검색한다' (Searches in a specific collection), which defines the tool's core action and resource. It differentiates from siblings like search_all_collections by specifying a single collection scope, though it does not explicitly compare.

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 provides parameter usage hints (e.g., collection codes, field options) and indicates a follow-up workflow using data_id with get_fulltext or get_translation. However, it does not explicitly state when to choose this tool over siblings like search_all_collections or search_in_dir.

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