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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is low, and the description still adds real context: data provenance (NZX disclosure notices), coverage window (multi-year from 2010), and richer semantics of the returned fields (nominee/company/individual/trust/fund, voting-rights percentages). It stops short of stating update cadence or data freshness/limitations.

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 what the tool returns; the field list earns its place by telling the agent what it gets. Slightly list-heavy but no filler.

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 return-shape explanation is a bonus rather than a requirement, and the description covers scope and provenance adequately. The one real gap is the unsupported 'all=true' reference, which is a completeness defect on the invocation side.

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% (baseline 3), but the description contradicts the schema by advertising a '?all=true' option that no parameter supports under additionalProperties:false, and its '?year=2025' query-string framing does not match the structured year/ticker fields. The year-is-historical clarification is useful, but the phantom parameter is actively misleading and could cause a failed call.

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?

States a specific verb and resource (top-20 shareholders + 5%+ substantial holders for an NZX company) and enumerates what the payload contains (HHI, holder types, YoY changes). It is clear on its own but never names or distinguishes itself from the many overlapping siblings such as get_substantial_holders, get_substantial_holder_notices, and get_beneficial_ownership.

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?

Provides only an in-line parameter hint ('Use ?year=2025 or ?all=true for historical data') rather than guidance on when to choose this tool over the sibling holder tools. No when-not conditions or prerequisites are stated, so the agent must infer selection from the sibling soup.

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