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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description is free to add substantive caveats it could not otherwise convey: 13F covers only long Section 13(f) positions with no shorts or cash, filing lags up to 45 days after quarter end, confidential positions may be omitted, and option/bond rows are excluded from share totals. It also discloses that the portfolio view is read live from EDGAR and that ticker matching resolves through issuer name with the match and other share classes returned for verification.

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 two directions and structured as parallel bullets, so an agent can scan to the relevant branch immediately. Slightly dense in the caveat paragraph, and the closing 'Not financial advice' is boilerplate that does not help invocation, though it is a single short clause.

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?

No output schema exists, so the description carries the full burden of describing returns, and it does: holder counts, total shares and value, top holders with quarter-over-quarter changes, and for the portfolio view positions by value with weights plus new/exited/increased/decreased classifications. Combined with the data-lag and coverage caveats, an agent has everything needed to call this correctly and interpret the result.

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 83%, so the baseline is 3, but the description adds genuine meaning beyond the schema: per-view defaults (20 holders vs 25 positions), the ticker-to-CUSIP matching behavior and its verification output, and the fact that managerName searches among 13F filers and may return multiple candidates. Only view-specific validation details, such as what happens with a malformed CUSIP, are left unstated.

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 (SEC Form 13F institutional holdings) and splits it into two explicitly labeled directions, view="holders" and view="portfolio", each with the exact data it returns. An agent can tell this apart from siblings like get_insider_activity or company_snapshot 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?

It gives an explicit routing rule: 'If the user asks "who owns X" vs "what does fund Y own", pick the view accordingly; if unclear, ask.' Each view also lists which parameters select it (ticker/cusip vs managerCik/managerName), and the multi-manager match case tells the agent to stop and confirm with the user before re-calling.

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