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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description's job is supplementary. It adds real behavioral context: live US Dept. of Labor data refreshed daily, a 50-most-recent-inspections cap that can skew counts, and the fact that chains/renamed sites appear under multiple establishment names. The one gap is it never says what the response object looks like (no output schema exists), though it does enumerate the aggregated fields.

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 aggregation statement, then usage questions, then an inline example call, then the data-source/cap caveat last. Every sentence carries information, though the enumeration of aggregated fields and the four quoted example questions make it denser than strictly necessary for an agent.

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?

With no output schema this description carries the full burden and meets it: it lists the returned aggregate fields, the data source and refresh cadence, the 50-record cap, and the multi-name matching caveat. An agent has everything needed to call it and interpret the result, including when the numbers may be truncated.

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% and the substring-match semantics of name are already documented in the schema. The description still adds value beyond the schema by explaining why state matters operationally: it is the lever for escaping the 50-inspection cap on national chains. That is genuine parameter guidance rather than restatement.

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 (rolled-up OSHA enforcement history for an establishment) and enumerates exactly what is aggregated: inspection count, violation count, initial/current penalties, most recent date, and distinct matching names. It explicitly distinguishes itself from the sibling osha_inspections as 'narrower and faster to read', so an agent can route without opening either schema.

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?

Gives the questions it answers ('has OSHA fined X', 'total OSHA penalties for X', 'how many times has OSHA inspected X') which map directly to user intents, and names the alternative (paging through osha_inspections yourself) along with the condition that favors this tool. It also advises narrowing with state to get a complete count on a national chain, which is conditional usage guidance beyond a simple recommendation.

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