lstrm_ai_search

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds useful behavioral context beyond that: AI-powered semantic matching, pagination behavior, multiple response formats, automatic ctx injection, and OC override. No contradictions with annotations.

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 well-structured with a brief intro and organized Args/Returns sections. It is front-loaded with a clear purpose statement. The Args list is a bit verbose with defaults repeated from the schema, but each line serves a purpose and the overall structure is easy to scan.

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?

The description covers purpose, parameters, and basic return info ('Search results or error'). However, it lacks details on the result structure, such as whether definitions are returned in a list or object format, and no examples are provided. Given the absence of an output schema, more detail about return shape would improve completeness.

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 carries the full burden. It compensates fully by explaining every parameter: query ('Search keyword'), display ('Number of results per page, max 100'), page ('1-based'), oc ('Optional OC override'), and type ('Response format'). This adds strong meaning beyond the bare 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?

The description clearly states 'Search legal terms using AI' and further specifies 'searches Korean legal terminology using AI-powered semantic matching. Returns definitions and explanations.' This is a specific verb+resource with explicit scope, distinguishing it from sibling tools like law_search or aiSearch that likely target statutes or general legal documents.

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 implies usage for AI-powered legal term lookup but does not provide explicit when-to-use guidance or mention alternatives among the many sibling search tools. There is no exclusionary language or comparison, so the agent must infer when this tool is preferred over others.

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