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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the bar is lower. The description adds real value beyond them: the result set is restricted to active employees, the payload is personal data, and the underlying OData path is disclosed. It doesn't cover default page size or rate limits, but those live in the schema.

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?

Three compact sentences, front-loaded with what the tool returns and its scope, then the sensitivity flag, the endpoint, and the sibling redirect. No filler.

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?

Covers purpose, scope restriction, PII caution, return fields, and the alternative tool — enough to invoke correctly without an output schema. Pagination and filter syntax are delegated to a well-described schema, which is reasonable.

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 top/skip/count/filter/select/orderby/company_id are already fully documented, and this is the baseline-3 case. The description adds only an indirect hint at the field vocabulary used by select/filter (name, employee number, contact, dates), nothing about syntax.

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 (List), resource (employees), and scope (active only) plus what data comes back (name, employee number, contact, dates) and the backing endpoint. The active-only qualifier and the pointer to payspace_list_all_employees make it unmistakable against both list and get siblings.

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?

Explicitly routes the terminated-employee case to payspace_list_all_employees, which is the main decision an agent faces here. It does not contrast with payspace_get_employee (single record) or mention paging strategy, but the list-vs-single split is inferable from the verb.

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