Bulk import requests (Pro)

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

With all annotations reading false/non-informative defaults, the description carries the behavioral burden and mostly meets it: it discloses that status defaults to pending, enumerates accepted status values, and — most valuably — states that conflicting rows are reported but not applied, i.e., partial application rather than all-or-nothing semantics. The 'watermark-free, full CRUD' tail adds ambiguity about whether updates/deletes are involved, slightly undercutting the otherwise strong disclosure.

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 sentences, front-loaded with the core purpose, then header format, then status and conflict behavior — good progressive structure. The final 'watermark-free, full CRUD' clause is the only non-operational content and reads like plan marketing rather than guidance.

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?

The input side is well covered for a one-parameter tool with no output schema: format, header, defaults, and conflict behavior are all present. The gap is the response — conflicting rows are 'reported' but the shape of that report and of a successful import is never described, and an agent cannot predict the return value. The Pro-license requirement is also only hinted at.

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?

The schema already documents the sole csv parameter at 100% coverage, but the description adds meaning the schema lacks: allowed status values (approved/rejected), the omission default (pending), and per-row conflict checking. It does not specify date or halfDay column formats, which remain undocumented in both places.

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?

Leads with a specific verb and resource — 'Bulk-create leave requests from a CSV/TSV' — which immediately distinguishes it from single-record siblings like leave_request, leave_approve, and leave_cancel. The header specification and status rules further pin down the operation. The closing 'watermark-free, full CRUD' phrase is slightly muddled but does not obscure the core purpose.

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?

The 'Bulk-create ... from a CSV/TSV' phrasing establishes a clear usage context: use this when many leave requests need to be created at once from a file, in contrast to the individual flow of leave_request. However, it never names an alternative or states when not to use the tool, and the 'Pro' prerequisite is a tag rather than an explained gating condition.

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