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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds value beyond them by disclosing result granularity ('up to 10 services per call') and data provenance (measurement dates, links, verification against each official site), which the annotations cannot convey.

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?

Front-loaded with the core operation and scoped in two efficient sentences, with the Korean rendering adding local nuance rather than pure duplication. Slightly longer than strictly necessary, but every clause contributes scope, query-mode, or return-format information.

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?

With nine parameters, no required fields, no output schema, and rich annotations, the description covers purpose, query behavior, and return shape. It omits pagination behavior (page capped at 3), the meaning of the filter enums, and any routing guidance among the four sibling tools, leaving gaps an agent must fill elsewhere.

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 56%, so the schema documents roughly half the nine parameters (try, sort, query, korean, category). The description only adds the notion that queries accept natural-language Korean or English and that filters exist; it does not explain the pricing, platform, page, or limit semantics. Baseline 3 is appropriate when the schema carries part of the burden.

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 names a concrete verb and resource ('Search AI services listed on AIFinder') and goes further by characterizing the directory (Korean AI-tool directory with verified Korean support, KRW pricing, business registration, trials). An agent immediately knows this is the discovery/search tool for the service catalog, but no sibling is named to disambiguate from get_ai_service or find_alternatives.

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?

Usage is implied: 'Accepts natural-language Korean or English queries and filters' conveys that you can search by keyword or browse by filters. However, there is no explicit when-to-use guidance, no statement of when to prefer get_ai_service or find_alternatives, and no prerequisites or exclusions.

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