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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond them: data provenance and refresh cadence ('Live US Dept. of Labor data, refreshed daily'), the substring matching semantics and their practical consequence, and the establishment-or-state requirement. It stops short of disclosing result ordering or pagination behavior, which keeps it off a 5.

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 scope, matching rules, return shape, requirements, examples, and the sibling hand-off. It is longer than a minimal definition, but nearly every clause carries information the agent needs (matching semantics, return fields, required inputs, alternative tool). Slightly dense with parenthetical enumerations.

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?

No output schema exists, so the description correctly carries the return-shape burden and enumerates it: address, NAICS, safety-vs-health, inspection type taxonomy, scope, open/close dates, and open-vs-closed status. Combined with the input constraint and the hand-off to osha_inspection for follow-up detail, an agent has enough to select and call this tool correctly.

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 the baseline is 3, and the schema already documents all four parameters including the substring matching rule. The description adds marginal but useful operational meaning — 'a shorter fragment of the name finds more' — plus restating the establishment/state-or-both constraint, which is a usage rule not encoded in the schema. Written in prose, the intent is clear and syntactically demonstrated with a worked example.

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+resource (OSHA inspections), its scope (establishment and/or state), and explicitly distinguishes itself from the standards data ('the enforcement record OSHA actually took, not the standards'). It also disambiguates from the sibling osha_inspection, which handles violations and penalties.

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 routing: 'Use osha_inspection with the returned activity_nr for violations and penalties.' It also states the hard precondition (requires establishment or state, or both), explains what `since` narrows, and maps example queries ('has OSHA inspected X', 'OSHA inspections in state X since Y') to concrete call shapes.

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