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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the description is not obligated to restate safety. It adds genuine value beyond them: the soundness screen (no warning filing in 12 months, assets > liabilities, 4+ audited years), the price basis (latest quarter-end 13F), and the framing that outputs are ranked screens rather than advice. It does not address response size or pagination for a 20-row-plus-supplemental payload.

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 core purpose is front-loaded in the first clause, which is good, but the single dense paragraph then strings together two unrelated supplemental datasets with long nested parentheticals. It reads as an accretion of every field the source produces rather than a prioritized briefing, and could be split or trimmed without losing calling guidance.

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 parameters and no output schema, the description carries the burden of telling the agent what comes back, and it largely does: ranking inputs, the $2B and soundness filters, and the field lists for the funds and monthly-payer sections (returns, worst month, holdings mix, yield, coverage, leverage, cuts, warning signs). Only the shape and boundaries of the combined response (three separate ranked sets) remain slightly ambiguous.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a 0-param tool applies. The description correctly implies the tool is unfiltered and returns a fixed weekly set, which is consistent with the empty 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?

The description names a specific resource and ranking method: top 20 US companies ($2B+) by cash returned to owners, computed from audited SEC filings, plus two secondary datasets (short-term funds from N-PORT, verified monthly dividend payers). An agent can tell it is a capital-return / income screening tool. It never contrasts itself with sibling screens like get_ai_leaders or get_energy_leaders, so differentiation relies on the topical wording alone.

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?

Usage is implied by the subject matter (screening for dividend and buyback strength) and clarified by the caveat 'Ranked screens, not recommendations'. There is no explicit statement of when to prefer this over the other leader screens, nor any exclusion of cases where get_company_performance or watch_company would be the better call.

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