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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds billing semantics that exist nowhere else — $0.0018 per ownership-row, and each returned row counts as one charged event (reinforced on maxResults). It does not mention rate limits, latency, coverage gaps (e.g. 13F lag), or pagination, so it is helpful but not complete.

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 capability is front-loaded in the opening clause and the four filing types are packed into one well-structured sentence, followed by a separate one-line pricing statement. It is dense rather than bloated, though the audience sentence ('For investors, analysts and AI agents') is pure filler and could be dropped.

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 13-parameter, all-optional, multi-mode tool with no output schema, the description does the important work: it tells the agent which filing family answers which question and warns that returned rows are billed. Left implicit are the shape of an ownership-row and the behavior of the default mode when no fund, filer, ticker, or cusip is provided.

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% and most parameters already carry per-mode applicability notes, so the baseline of 3 applies. The description adds a little beyond the schema by explaining what 13D vs 13G and Form 144 mean in substantive terms, but it adds nothing about parameter interplay — e.g. that filer vs ticker/cusip are alternative lookup paths within holdings13f, or what happens when mode is left at its default with no subject supplied.

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 precise verb and resource — who owns a stock and who is about to sell it, sourced from official SEC filings — and enumerates the four filing families (13F, N-PORT, 13D/13G, Form 144) with concrete examples (Berkshire Hathaway, VOO, ARKK). It does not, however, differentiate itself from the sibling sec_insider_trades, even though planned144 (insiders filing to sell) clearly overlaps with that tool's territory.

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 routed through real scenarios: fund-manager holdings with quarter-over-quarter changes, mutual fund/ETF holdings, holders of a ticker, 5%+ stake filers split into activist vs passive, and insider sell intent. That gives an agent clear conditions for choosing a mode. It stops short of exclusions — nothing says when to prefer sec_insider_trades, sec_filings_feed, or sec_company_financials instead.

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