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

Annotations only declare readOnlyHint; the description adds the real behavioral context: the screening universe and its exclusions, that ratios are decimals (0.04 = 4%), each preset's threshold logic and sort key, and an explicit cost of 10 tokens. These are all facts an agent cannot get from the schema or 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?

Front-loaded with purpose and universe constraints, and every preset clause carries distinct information. However the pipe-delimited run-on block of six presets is dense and hard to scan, and the trailing Japanese sentence largely restates the preset list already given in English.

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 no output schema, the description should clarify what comes back; it says 'ranked list' and specifies the sort key per preset, which is adequate. It does not describe the fields in each result row or behavior when fewer than 'limit' names match, leaving a minor gap.

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 67%, and the description compensates well for the key parameter by spelling out what each enum value actually filters and sorts on. It does not add anything about limit (default 50, max 100) or the sector code pattern, which are left to the 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?

States a specific verb (run) and resource (ready-made screen), names the universe (Japanese common stocks, cap >= JPY 5B, preferred/class shares and TOKYO PRO Market excluded) and the output (ranked list). This clearly distinguishes it from the custom-criteria sibling screen_stocks and from get_rankings.

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 six preset names, their exact filter criteria and sort orders give an agent concrete grounds to pick the right preset for a high-dividend, value, ROE, growth, dividend-streak or momentum request. It stops short of explicitly routing away from screen_stocks for custom criteria, so the when-not case is implied rather than stated.

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