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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds genuinely useful context beyond that: the source (NJ Department of the Treasury Ineligible Provider List, keyless), the 4,000+ row scope, that counts span the whole list rather than a page, and that notes flag gaps in the status field and the ever-vs-currently-excluded distinction.

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?

It is a single dense paragraph that front-loads what the data covers and then the counting mode, with no filler sentences. It is somewhat long and repeats the 'whole list, not a page' point that the schema also makes, which keeps it from a 5.

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, the description carries the burden of describing returns and does so — it lists the aggregates, the action-type breakdown, the date extremes, and the status-field caveats. Coverage is strong for a zero-required-parameter metadata tool; only the explicit hand-off to the screening sibling is absent.

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 schema already documents all three parameters and the baseline is 3. The description goes further by naming the field actually being counted (effective_date, Treasury's Effective Date) and restating the precedence rule ('ignored if start_date/end_date are given') in operational terms, which adds meaning the schema only states structurally.

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 resource and enumerates exactly what it reports (row totals, current/ended/unknown status, NPI/Vendor ID coverage, action types, oldest/newest effective dates), so the agent knows this is a dataset-profile tool. It references 'the screening data' but never names the sibling nj_medical_check_exclusion, so the boundary with the actual screening tool is implied rather than stated.

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?

It gives a clear use condition — 'check the screening data is fresh enough to rely on before a compliance decision' — and explains the secondary counting mode with year or start_date/end_date. What is missing is the explicit routing statement telling the agent to use nj_medical_check_exclusion when it actually needs to screen a provider, which would make this a 5.

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