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

Beyond the readOnlyHint annotation, the description discloses substantial behavioral context: VCP detection is an 'APPROXIMATION (heuristic swing/contraction count, not a discretionary chart read)', prices are 'adjusted for corporate actions but not dividends', US history has known start dates that affect long-window figures, and RS percentile interpretation is explained. It even clarifies that an empty result is not an error and what a specific database error message means.

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 long but justified by the tool's complexity (12 parameters, 8 screening criteria, multiple markets). It is well-structured with clear sections: criteria list, arguments, return shape, examples, use-when, notes, errors. It drops one point because the Arguments section partially repeats schema descriptions and the 8-criteria list, while valuable, adds substantial length; a slightly tighter version would be even more concise.

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 is complete for a complex screening tool: it covers the data source snapshot, all filter semantics, return fields, sorting options, example invocations, concrete use/when-not-use guidance, data caveats (dividends, US history start), and error conditions. The output schema likely exists, but the description also spells out the expected return object, leaving the agent with everything needed to call the tool correctly.

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%, so the baseline is 3, but the description adds meaningful context beyond the schema: it explains why each parameter matters (e.g., 'min_price' avoids penny stocks with example values for US$ and KRW), how 'near_high_pct' relates to tightness, and that 'rs_min' has a Minervini preference for higher values. While the field-level descriptions in the schema are already strong, the tool description enriches them with rationale and examples.

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 specific verb and resource: 'Screen KR, US and/or TW stocks that pass Mark Minervini's 8-point Trend Template.' It explicitly names the methodology, the underlying data snapshot, and the return focus ('stage-2 uptrend leaders'), making the tool's purpose unambiguous and easily distinguished from siblings like screen_technical or get_technicals.

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 apply the tool: 'finding stage-2 momentum leaders (Minervini/CAN SLIM style).' It also gives explicit exclusions: 'Don't use for a single stock's detail (get_technicals), fundamentals (screen_companies/get_valuation), or arbitrary technical signals (screen_technical).' This gives the agent clear routing guidance.

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