get_holders

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description needn't restate safety. It adds genuinely new behavioral context: institutional/fund data comes from quarterly filings and may be months stale while insider trades are filed within days, and missing data for a category returns a short message rather than erroring. It stops short of describing pagination or row limits on large holder lists.

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, then categories, then usage and exclusions, then output/freshness caveats — a sensible order. The long parenthetical enumeration of all six enum values duplicates what the schema already documents, costing some efficiency in an otherwise tight description.

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 an output schema present, return-value detail is unnecessary, and the description covers everything else an agent needs: what each category yields, one-category-per-call behavior, explicit sibling routing, output format, data-staleness expectations, and empty-result behavior.

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% and the schema's own holder_type description already enumerates the same categories, so the description largely restates structured data. The added value is marginal — it clarifies intent of ambiguous values like 'major' and 'insider_purchases' slightly more conversationally than the schema, but adds no format or syntax detail.

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+resource ('Ownership and insider activity for one stock') and then enumerates each of the six holder_type categories with a plain-language meaning ('one row per trade', 'insider-vs-institutional ownership % breakdown'). An agent can tell exactly what data it gets without opening the schema.

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?

Gives positive triggers ('who owns X', institutional ownership, insider trading activity), an operational constraint ('One holder_type per call: call again to get a different view'), and explicit exclusions routed to named siblings: share count/float/valuation to get_company_info, analyst opinion to get_analyst_recommendations.

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