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

Beyond the readOnlyHint annotation, the description discloses the result cap (15), the teaser/truncated nature of the output, and that the response carries an app link to the full screener — meaningful behavioral context. "Read-only" merely restates the annotation and earns no extra credit.

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 action and result size, then the teaser limitation. The trailing "Read-only." is redundant with the annotation and slightly wasteful, but the rest earns its place.

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?

For a two-optional-parameter read-only screening tool with no output schema, this covers what it returns (bounded list, app link) and its limitations. Nothing an agent needs to invoke it correctly is missing.

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 100%, so sector and min_score are already fully documented in the schema. The description adds no meaning about how filtering interacts with the score ranking or what happens when min_score excludes everything, so baseline 3 applies.

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 and resource ("Screen the Returnolio universe") plus a concrete result bound ("up to 15 top-scored names"), which tells an agent exactly what comes back. It does not differentiate itself from the sibling screen_stocks, leaving ambiguity about which screener to pick.

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?

"This is a teaser, not a bulk export; the full screener with all filters is in the app" gives a useful when-not signal and points to the app for depth. However, it never addresses the obvious alternative in the toolset, screen_stocks, nor states when a company screen is preferable to a stock screen.

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