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

Despite readOnlyHint=true and openWorldHint=false already signaling safety, the description adds material behavioral context: KR vs US data availability, null NAV/AUM for US, price-return vs total-return semantics, same-day premium computation, AUM currency caveat, and the one-calendar-year pinning of total_return_pct. It also documents the 'database has not been built yet' error and that empty results are not an error. No annotation contradiction exists.

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 warnings, per-market coverage, args, examples, and use-when sections, and it front-loads the core purpose. It is, however, longer than strictly necessary: the 'Args' and 'Returns' sections largely repeat information already present in the input and output schemas, so a few sentences add redundancy rather than new signal.

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 definition is complete for a complex, 13-parameter screening tool: it covers market-specific behavior, result semantics, sort options, error cases, and provides four representative invocation examples. The output schema already specifies the return shape, and the description supplements with caveats an agent needs to avoid producing misleading tables.

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 coverage is 100%, but the description goes well beyond the schema: it gives a concrete min_aum conversion example (100000000000 = 1,000억), explains that premium_pct is same-day close/NAV-1, shows how index_contains finds 'TR' or '코스피' trackers, and clarifies that total_return_year can be omitted for the best-covered year. These are semantics an agent could not derive from property descriptions alone.

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 a concrete verb and resource: 'Screen exchange-traded funds in the local finbridge database' and immediately names the differentiating fields (NAV premium, AUM, index, momentum, total return). It also distinguishes itself from screen_companies, so an agent can discriminate among sibling screening tools without inspecting their schemas.

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 'Use when' section states exactly when to call it ('choosing or comparing funds') and explicitly says not to use it for stocks (screen_companies) or single-fund price history (get_stock_prices). The coverage-per-market and excluded-funds notes further narrow when this tool is appropriate.

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