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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: the scores are pre-computed rather than live analysis, derived from scanning announcements, and it flags 'first-time detections' as an early-warning signal, telling the agent how to interpret the output.

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 purpose, then categories, then return shape, then usage triggers. Dense but every clause earns its place; the return-field enumeration is long but useful routing/inventory context.

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 returned fields need not be re-explained, yet the description still summarizes them helpfully. Combined with annotations and full param coverage, an agent has what it needs; only the missing sibling differentiation keeps it from a 5.

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?

Only one parameter (ticker) with 100% schema coverage, including example values, so the schema does the work. The description adds no format or validation meaning beyond the schema's baseline, so a 3 is correct.

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 (Get) and resource (pre-computed risk language scores) plus scope (NZX company, scanned from NZX announcements). Enumerating the 8 risk categories makes it concrete and separable from narrative/disclosure siblings.

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?

Explicit 'Use when asked about...' list covers risk factors, going concern, covenant, litigation, first-time risk language, and regulatory risk. It gives clear positive triggers but never names when-not-to-use or the closest alternative (e.g. analyse_narrative_risk, get_disclosure_language), so routing between overlapping tools is left to inference.

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