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

Goes well past the annotations: discloses $1.00 per person added cost (nothing if none found), all-or-none atomicity, loop refusal on manager cycles, status derivation from past end_date, and that each saved person returns a person_id. Rich behavioral context for a non-annotated cost-bearing operation.

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?

Dense but front-loaded, with each sentence carrying real information (batch limit, matching, clearing semantics, manager cycles, cost). Reasonably sized for the complexity, though a few clauses (e.g. status-from-end_date) could be tightened.

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?

For a single-array-parameter upsert with nested per-person objects and no output schema, the description covers matching, clearing conventions, manager validation, cost, and that person_ids come back. Nothing essential to correct invocation is missing.

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 0% per context, so the description must compensate; it does with useful rules like "" clears text, null clears a date, first_name required for new people, and manager accepts id/email including someone added later in the same call. It doesn't detail every one of the ~20 fields, but covers the critical ones.

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+resource (add/change people), the batch limit (up to 100), and the atomic all-or-none semantics. It clearly distinguishes itself from hr_adjust_leave and the admin_save_person sibling by explaining the upsert-matching model.

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?

Gives explicit routing: use hr_adjust_leave when adding people partway through a leave year to record prior usage/carryover, and explains the matching order (person_id then work email). It doesn't discuss hr_get_person or hr_list_people, but the when-to-use context is clear.

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