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

Annotations already declare readOnlyHint, idempotentHint and non-destructive behavior, so the description doesn't need to re-state safety. It adds genuinely non-obvious behavior instead: point-in-time semantics where 'filings after as_of are hidden,' and a tier gate where free keys see only the last 12 months while full history requires a FinzData plan. It does not cover error behavior or result volume, which is why it isn't a 5.

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?

Three sentences, front-loaded with the user question the tool answers, then the input form, then the temporal and plan constraints. Every sentence carries distinct information with no repetition of the title or annotations.

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 two-parameter read tool with no output schema, the description covers what is returned (13F holdings as known on as_of), the default for the cutoff, and the plan-based depth limit — enough to call it correctly. What remains unstated is the shape of the response and how large a holdings list typically is, a minor gap given the low complexity.

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 50%: as_of is well documented in the schema, but query has no schema description at all. The description compensates by explaining that query accepts either a manager name or a ticker and by restating the as_of cutoff as a look-ahead guard, giving meaning beyond the bare string type. It still doesn't say how ambiguous or partial names are resolved.

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 concrete verb+resource pair (retrieve 13F holdings) and frames the query intent as 'who owns this stock, and what does this manager hold?' — exactly the two access patterns the tool supports. That framing distinguishes it from neighboring data tools like get_fundamentals_pit or get_political_spending without the agent needing to open any 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 tells the agent precisely what to put in the query ('a manager name (BERKSHIRE) or a ticker (AAPL)'), which is the main usage decision for this tool. It provides clear context and examples but never names an explicit alternative sibling or a when-not-to-use condition, so it stops short of full routing guidance.

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