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

The annotations declare destructiveHint=true and idempotentHint=false, and the description reinforces this with concrete destructive semantics: it 'Replaces the complete content' and 'omitted items and their selections are deleted,' plus a warning not to send a partial list. It also discloses auth needs ('Requires OAuth') and the return shape (updated bill and the same share_url), adding context well beyond what annotations convey.

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?

It is front-loaded correctly, opening with purpose and when-to-use before edge cases. However, it is very long and several statements restate rules already carried by the 100%-covered schema (item total equals unit_price times quantity, tax allocation, total reconciliation), and the instruction blocks stack without clear visual separation, diluting scannability.

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 destructive, multi-parameter mutation with nested objects, the description covers the full replacement model, ID semantics, currency constraints, tip/portion math, rounding-clarification behavior, and the returned share_url. With an output schema present it need not detail return values, and the remaining gaps for correct invocation are effectively closed.

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, but the description adds operational meaning beyond the schema: preserving existing item IDs vs. using an empty ID for new items, the rule that item total_price must equal unit_price times quantity, the bill-level reconciliation rules, and the tip/share-division procedures. Much of this complements rather than repeats the schema, though the tax and total-equality rules overlap with schema text.

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 names a specific verb and resource (edit an existing shared bill) and enumerates the concrete edit types it supports: correcting items, renaming, add/remove purchases, tips by participant count, and dividing shared dishes. It also explicitly distinguishes itself from siblings by naming create_bill and set_bill_selections_batch and the cases they own. An agent can route correctly without reading any 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 an explicit when-to-use clause, an explicit when-not-to-use clause (new bill, hypothetical question, recording participant choices), and names the exact alternative tool for each excluded case. Nothing about tool selection is left to inference.

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