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

Annotations already cover read-only and non-destructive behavior. The description adds useful behavioral context: data coverage nuances (full/partial/unknown when counts are missing) and the ordering convention. It does not describe potential errors or return format, but with annotations in place, this is a strong addition.

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 convey the core function, a data-quality caveat, and pagination guidance. Each sentence adds distinct information without redundancy. It is front-loaded with the main purpose, making it easy to parse quickly.

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 simple read-only query tool with pagination, the description covers the essential aspects: source (NPORT-P), ordering, coverage, and how to paginate. The lack of an output schema is mitigated by the fact that the tool's purpose is straightforward. A mention of return structure would be nice, but it is not critical given the simplicity.

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%, so all three parameters (ticker, offset, maxResults) are already documented. The description adds a note about offset for 'broad portfolios', but this largely mirrors the schema's 'Number of ranked holdings to skip'. Thus the description provides minimal extra value beyond the schema, warranting the baseline score of 3.

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 uses a specific verb ('Get') with a clear resource ('an ETF's stored portfolio holdings') and specifies the data source ('latest SEC Form NPORT-P report') and ordering ('largest position first'). This distinguishes it from sibling tools like GetEtfProfile (profile data) and GetTopHolders (likely stock-focused), even without naming them.

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 context about data coverage ('full, partial, or unknown') and pagination ('Use offset to continue through broad portfolios') but does not explicitly state when to use this tool versus alternatives. It neither names sibling tools nor provides exclusion criteria, leaving the selection logic to the agent's inference.

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