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

With readOnlyHint/idempotent/openWorld already declared, the description still adds real behavior: the source is AHCA's keyless Public Records final-orders search, counts run over the WHOLE 7,000+ row list rather than a page, and the response separates participation_exclusion_count (true exclusions) from all_sanction_orders_count (which includes fines/CAPs). That distinction and the freshness caveat are exactly the context annotations cannot carry.

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 front-loaded with the data-coverage summary before the parameter behavior, and nearly every clause adds content. It is dense and run-on, however, packing coverage inventory, usage, parameter modes, and return-field semantics into two long sentences, and the aside 'the response says which is which' is slightly redundant.

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 return-value burden and does name the two key count fields while enumerating the other coverage figures. It also confirms the data source and keyless access, leaving an agent with enough to invoke and interpret it correctly; only finer field naming 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 all three params are documented in the schema, including the year-ignored-if-range-given precedence. The description restates that mode switch and frames year as answering a specific count question, adding only marginal semantic value beyond what the schema already provides, so the baseline 3 applies.

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 concretely enumerates what the tool reports (total final orders, participation exclusions vs fines/CAPs, distinct providers, NPI/license/Medicaid-number counts, violation-code counts, oldest/newest sanction dates, capture date) and its counting mode, so the verb+resource is unambiguous. It implies a screening counterpart ('check the screening data is fresh enough') but never names the sibling fl_medical_check_exclusion, so differentiation is only inferable 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?

It states clear contexts for use: verifying the pack is fresh before a compliance decision, reading the sanction-vs-exclusion notes, and answering count questions like 'how many Florida Medicaid exclusions took effect in 2025'. It routes between year and start_date/end_date modes, but never explicitly says when NOT to use it or names the alternative tool for actual screening.

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