Zovo Bill Splitter

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

Annotations declare readOnlyHint and destructiveHint=false, but the description adds substantial beyond-annotation context: balances sum to exactly zero, the tool computes the fewest payments, mixed currencies are rejected with no conversion, and it does not send payment requests, move money, or persist the group. These are behavioral guarantees an agent can't get from the annotations alone.

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?

Front-loaded with when-to-use, then split modes, then return values, then boundaries and sibling routing. Dense but every sentence carries information; 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?

A read-only computation tool with an output schema and full param coverage. The description still adds the zero-sum guarantee, minimal-payments property, currency constraint, and non-persistence, which are the things an agent most needs to trust before calling.

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 the schema already documents split modes, split_among, and split_values. The description reinforces the four split modes and the one-currency-per-call constraint, but adds little semantic detail beyond the schema. Baseline 3 is appropriate.

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 (settle group expenses) and immediately scopes it to multi-expense groups like trips, roommates, and events. It explicitly distinguishes itself from the sibling split_bill by telling the agent to use split_bill for a single restaurant bill.

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 a clear triggering condition ('several shared expenses paid by different people') and an explicit exclusion routing to the alternative ('for one restaurant bill use split_bill'). Mixed-currency rejection and the no-money-movement boundary are also spelled out, so the agent knows when this tool is and isn't appropriate.

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

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

The description adds substantial behavior beyond the annotations: tax, tip, and service charge are shared proportionally to pre-tax subtotal, shares are exact to the cent using largest-remainder rounding, and paid_by produces who-owes-whom output. It also discloses practical limitations such as no photo OCR and no currency conversion.

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?

The description is front-loaded with the primary use case and then layers in exclusions and behavioral notes. Despite covering a complex 18-parameter tool, every sentence carries actionable information.

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?

Given the rich input schema, existing output schema, and clear annotations, the description supplies the remaining high-value context an agent needs. It covers when to use it, key calculation behavior, and the main boundaries relative to alternatives.

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 the baseline is 3 even without extra parameter explanation. The description adds useful semantics around proportional sharing and exact cent rounding, though it does not discuss most of the 18 parameters directly.

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 uses a specific verb and resource, 'split ... bill', and defines scope as a single bill between people, including even or itemized splitting. It also distinguishes itself from the sibling tool settle_group_expenses for many bills or several payers.

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 explicitly states when to use the tool, including restaurant bills, receipts, takeout orders, and single bills. It also gives clear exclusions and alternatives: no receipt-photo reading, no multiple payers or many bills (use settle_group_expenses), and no currency conversion.

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

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

The annotations already establish that this is a read-only, idempotent, non-destructive operation. The description adds useful behavior beyond that: every amount is exact to the cent and the parts add up exactly to the rent, and it clarifies that the tool does not collect rent or give legal advice.

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?

The definition is front-loaded with the usage trigger and then adds the arithmetic guarantee and exclusions. The first sentence is dense with many clauses, but overall there is little wasted text and no repetition of schema details.

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 seven-parameter tool with a full output schema and strong annotations, the description covers purpose, supported splitting bases, arithmetic guarantees, and key exclusions. An agent has enough information to decide when to call it and what behavior to expect.

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 the schema already documents all seven parameters in detail. The description reinforces concepts such as shared-space splitting per occupant and per-room adjustments, but it does not add syntax or edge-case semantics beyond what the schema provides.

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 states a specific verb and resource — splitting rent among roommates — and enumerates the supported bases (room size, income, equal), adjustments, couples, and utilities. It also distinguishes itself from settle_group_expenses for one-off shared expenses, so an agent can tell what it is for without opening the schema.

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 gives a clear trigger (roommates or housemates wanting to split rent fairly) and an explicit exclusion for one-off shared expenses with a named alternative, settle_group_expenses. The other sibling, split_bill, is not mentioned, leaving a small gap in routing guidance.

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