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

With no annotations, the description carries the full burden. It does disclose a real behavioral trait beyond the schema: rounding to the cent with shares guaranteed to sum exactly to the total. But it says nothing about edge-case handling (zero-hour participants, zero total hours), whether the call is a pure computation with no side effects, or what the result looks like.

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?

One sentence, front-loaded with the operation and followed immediately by the allocation and rounding guarantee. Nothing is wasted and nothing competes for attention.

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?

There is no output schema, so the description should ideally sketch the return shape (per-person amounts, ordering, whether the total is echoed). It covers the allocation rule well but leaves the response contract and edge cases unaddressed for a two-parameter computational tool.

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 50% — only total_tips carries a description ('US dollars'), while the people array and its hours field are undocumented. The description partially compensates by establishing that hours are the proportional weight, but it does not clarify units, allowed ranges, or duplicate-name handling.

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 gives a specific verb and resource ('Splits a tip pool by hours worked') plus the allocation rule, which is enough to distinguish it from the payroll-calculation siblings (calculate_time_card, convert_decimal_hours, overtime_pay). It stops short of naming those siblings explicitly, but the operation is unambiguous.

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?

There is no guidance on when to use this versus the sibling payroll tools, and no stated preconditions — nothing about whether hours may be zero, whether the array may be empty, or what happens if total hours sum to zero. The agent must infer all invocation conditions.

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