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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavior beyond them: this is a CURRENT SNAPSHOT, not an ever-excluded history, so a reinstated provider vanishes from the next monthly file; counting runs over the whole list, not a page; and the counted field is effective_date (NC Medicaid's EFFECTIVE DATE column). These are non-obvious semantics an agent could not derive from structured 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?

Purpose and snapshot caveat are front-loaded, then the parameter-driven counting mode, so the structure is sensible. It is dense and slightly run-on with multiple parenthetical em-dash asides, but nearly every clause carries distinct information rather than padding.

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 zero required parameters, the description does the heavy lifting: it enumerates the reported fields, explains the snapshot-vs-history distinction, and states which date field backs the count. Return shape is described at a summary level rather than exhaustively, which is adequate for a statistics tool but leaves the exact response structure only partially specified.

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. The description goes beyond the schema by naming the field being counted (effective_date, NC Medicaid's own EFFECTIVE DATE column) and reiterating that counts span the whole list rather than a page and that year is ignored when start_date/end_date are supplied — meaningful semantics the schema alone doesn't convey.

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 names a specific verb and resource: reporting what the NC Medicaid State Excluded Providers List covers (row totals, NPI vs. atypical ID split, distinct exclusion reasons, oldest/newest effective dates) plus a count-by-date mode. It is clearly a coverage/statistics tool, distinct from a per-provider lookup, but it never names the likely sibling nc_medical_check_exclusion, so the differentiation is implied rather than explicit.

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 context is clear: ask it for list-wide coverage questions, or pass year / start_date / end_date to count exclusions taking effect in a period, with the example question 'how many NC Medicaid exclusions took effect in 2025' grounding the intent. It does not, however, state when NOT to use it or point to the sibling check tool for individual provider lookups, so the alternative is left to inference.

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