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

Annotations declare the safety profile (readOnly=false, idempotent=false, openWorld=true, destructive=false), and the description still adds valuable operational context beyond them: OAuth requirement, no profile lookup needed, the fact that anyone with the returned share_url can view the bill, and the non-idempotency caveat about not blindly retrying after a timeout or ambiguous server error. It also discloses validation semantics (fixed control total, no invented taxes or adjustments) that annotations cannot express.

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?

Purpose, example and exclusions are front-loaded, but the body is a dense run-on that repeats rules already stated verbatim in the item unit_price and total_price schema descriptions (standalone tax items, not double-adding included taxes). Several clauses about reconciliation, tips and splits are useful, yet the sheer length and duplication make it harder to scan than it needs to be.

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 mutation tool with nested objects and an output schema, this covers everything an agent needs: currency handling, total reconciliation, tax allocation, tip and split rules, retry policy, and auth. Return values are already covered by the output schema, and the description still names share_url and the bill UI, so nothing material 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 100% with rich nested descriptions, so the baseline is 3, but the description goes further by showing how inputs map to fields concretely (pizza 1 x 20, beer 2 x 5, bill total EUR 30), by requiring positive quantities / nonnegative prices / a single currency, and by explaining that quantity encodes participant count for shares and tips. It largely restates the schema's tax and total rules, which caps it at 4 rather than 5.

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 first sentence gives a specific verb+resource+outcome: create and share an itemized bill with a participant-selectable link. It also names the sibling it is not (update_bill), so an agent can separate it from update_bill, set_bill_selections_batch and get_current_user_profile without opening 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?

Explicit when-to-use (bill creation for a meal or shared purchase, from photo, typed list or prose) and explicit when-not (reading a receipt, simple arithmetic, collecting payments, booking a restaurant), plus the named alternative for edits. 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.