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

Annotations already mark this as read-only and idempotent, but the description adds substantial behavioral detail: grouped-mode semantics for holdings_count/shares_owned_total, row field guarantees, no-holdings filings behavior, split-adjusted filter advice, pagination limit, dynamic credit cost (including charges on empty results and 504 timeout), and plan restrictions. This is far beyond what annotations provide and fully discloses operational caveats.

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 dense but well-organized: it starts with purpose, then filter mechanics, output behavior, edge cases, pagination, cost, and plan requirements. Every sentence carries useful information, though the length is substantial. It is front-loaded and each clause earns its place, so this is strong but slightly heavy for a 10% weight.

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 complex tool with 12 parameters and no output schema, the description is remarkably complete. It clarifies return row fields, grouping semantics, edge cases for no-holding filings, cost and timeout behavior, plan limits, endpoint, and documentation pointer. An agent has enough context to invoke the tool correctly and anticipate results without needing to read external docs.

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 baseline is 3. The description adds meaningful parameter semantics by explaining how holding_filters and aggregate_filters work together, the operators allowed, the grouped-vs-flat interpretation of aggregate metrics, and the split_adjusted_shares_owned guidance. It doesn't enumerate each parameter but adds context beyond the schema fields, earning a 4.

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 states a specific action ('Screen Form 3 holdings across the whole library') and resource ('initial holdings'), with concrete filter dimensions (holding_filters, aggregate_filters). This clearly distinguishes it from siblings like search_institutional_holdings or list_initial_holdings, so an agent can tell them apart without opening their schemas.

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 description gives clear context: this is a screener for Form 3 holdings over the whole library with both holding- and company-level filters. It doesn't explicitly name alternatives or state when not to use this tool, but the role is unambiguous given the filter capabilities and scope, so it provides enough context without exclusions.

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