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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds real behavioral context beyond that: the eight scoring dimensions, the 0-100 range, sector benchmarking with percentile, and the five rating bands — enough for an agent to understand what the returned score means.

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 core purpose, then the scoring model, then the use cases. The dimension enumeration is long but each item is informative rather than filler, and there is no redundant restatement of annotations or schema.

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 return values need no explanation, and the description still supplies the interpretive context (dimension set, scale, sector percentile, rating bands) an agent needs to use the result. Combined with full param coverage and confirming annotations, nothing material is missing.

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, and the schema already documents it at 100% coverage including NZX ticker examples ('FPH', 'AIR', 'SPK'). The description adds nothing about ticker format or resolution beyond what the schema provides, so the baseline of 3 applies.

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?

Specific verb+resource ('Get annual report quality score for an NZX company') with the composite's composition, 0-100 scale, rating bands, and sector percentile made explicit. The dimension list implicitly separates it from siblings like get_disclosure_score or get_ir_quality, but it never names or contrasts an adjacent tool, so it stops short of full sibling differentiation.

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 final sentence gives clear triggering contexts: annual report quality, disclosure completeness, reporting standards, and reporting transparency. It states when to use it but offers no when-not-to-use guidance or routing to similar-scoring siblings such as get_disclosure_score or get_accounting_quality.

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