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

Annotations already cover readOnlyHint, destructiveHint and openWorldHint, so the bar is lower, yet the description still adds substantial interpretation context: median_tenure_days is computed over people who already left, and churn_rate is leavers over everyone who ever worked in that slice rather than a per-period rate. These are exactly the disclosures that prevent misreads of a read-only analytical tool; it does not describe output shape or aggregation granularity, keeping it from 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 the identity of the report, then the two critical reading caveats, then the period-filter rule. Every sentence carries information, though the heavy ALL-CAPS emphasis and the 'begins where recruiting ends' framing are slightly verbose for the payload delivered.

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 and five optional filters, the description gives enough to call the tool correctly and interpret its key metrics, including the filter semantics. Gaps remain around default period behavior, whether breakdowns are returned nested or as separate rows, and how 'reason' relates to the dedicated dropoff-reasons sibling.

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 0% across five parameters, so the description must carry the load. It does clarify the single most important semantic — that since/until filter the LEAVING date, not the hiring date — but says nothing about date format, timezone, or the meaning of location_id, org_unit_id and position_id (which are only inferable from their names).

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?

The description states a specific verb-and-resource pair ('Staff TURNOVER ... answers how long do people last and why do they leave') and demarcates its domain ('the employment side, which begins where recruiting ends'), which separates it from recruiting-side siblings. It stops short of naming a concrete alternative such as hr_dropoff_reasons_report, which sounds like it could overlap on the 'why they leave' axis.

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 through domain framing and the caveat about reading two numbers together, but there is no explicit when-to-use/when-not guidance and no routing to a sibling when the agent wants recruiting-side or reason-only data. The agent must infer selection from the domain description alone.

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