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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is fully covered. The description adds the methodological anchor ('per 200,000 hours, the way BLS does'), which is genuine extra context, but it omits behaviorally relevant details such as how zero or missing hoursWorked is handled and whether the optional deaths field feeds into TRIR.

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?

A single tight sentence that front-loads the verb and the outputs with zero filler. Nothing to cut and nothing buried.

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 stateless calculator with a fully described five-parameter schema and no output schema, the description covers what is computed and the rate convention. It falls short of 5 only in not indicating which returned rates each input contributes to (especially the optional deaths field) or the constant-hour denominator's handling of edge cases.

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%, so the baseline is 3; the description edges above it by naming two of the five inputs' conceptual roles (days-away cases, hours worked) and clarifying the 200,000-hour multiplier. It still does not map required fields like restrictedCases or otherCases to the specific rates they feed, but with the schema fully documented that gap is minor.

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 ('Compute') plus three named outputs (TRIR, DART, days-away case rate) and the normalization basis (per 200,000 hours). This is clearly a calculation tool, distinct from sibling determination tools like osha_is_recordable or osha_coverage.

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?

Usage is implied: you call it when you have case counts and hours worked and need incidence rates in the BLS style. However, it never states when to prefer this over siblings such as osha_is_recordable (classification) or osha_hearing_shift, nor any prerequisites or exclusions.

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