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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds some value beyond that: scope is limited to the *latest* filing plus a comparison against the immediately prior quarter, so the agent knows this is not an arbitrary historical range. It says nothing about 13F reporting lag (filings trail quarter-end by ~45 days), manager-name matching behavior, or coverage gaps – relevant for a data-lookup tool but not disqualifying given the annotations.

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 payload contents, then the change data, then intent examples – a sensible order with no filler. The opening sentence is long and runs the return contents and the comparison set together, costing a little readability.

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?

An output schema exists, so the description needn't restate return shapes, and with 100% schema coverage the parameters are self-documenting. What's still missing for correct invocation is the freshness contract (13F filing lag) and any hint about how loosely 'manager' is matched, plus the boundary against get_institutional_ownership.

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%: both 'manager' and 'top' are already documented in the schema with bounds and examples. The description reinforces semantics implicitly ('top holdings with % of portfolio' explains what 'top' controls, and the example queries clarify what kind of string 'manager' accepts) but adds no format or matching rules beyond the 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?

Names a specific resource (a fund's latest SEC Form 13F portfolio) and enumerates exactly what it returns: total value, position count, top holdings with percentages, plus quarter-over-quarter changes (new, sold out, biggest adds/cuts). That is far beyond a restatement of the name. It stops short of 5 because it never distinguishes itself from the sibling get_institutional_ownership, which an agent could plausibly confuse with this.

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 three quoted example queries ('what did Berkshire buy last quarter?', 'top holdings of Bridgewater', 'did Ark sell Tesla?') map concrete intents onto this tool, which effectively tells an agent when to pick it. It gives no explicit exclusions or pointer to an alternative for overlapping ownership data.

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