Update estimate

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds real context beyond them: Wave's underlying patch requires customer, status, title, dates, currency and exchange rate, and this tool backfills omitted ones from the current estimate. The warning that 'Passing items replaces every line' is the key destructive side effect and is not derivable 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?

Two tight sentences, front-loaded with the purpose and then the two highest-value behavioral caveats (fill-forward defaults, destructive item replacement). Nothing is wasted, though a little more structure (e.g., separating the destructive warning) would improve scanability.

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 33-parameter destructive mutation with no output schema and low schema coverage, the description covers only the minimum viable surface. It says nothing about permissions, what happens to an estimate already sent/accepted, whether acceptance state resets, or limits beyond the items-array note, all of which matter when mutating an estimate.

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 only 27% across 33 parameters, so the description must compensate, and it partially does by explaining the fill-forward behavior for customer/status/title/dates/currency/exchangeRate and the replace-all semantics of items. However, the bulk of parameters (hiding flags, subhead, footer, itemTitle, payment disablers, deposit fields) receive no additional meaning from the description, leaving much of the surface 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?

The description opens with a specific verb+resource ('Change an estimate') and immediately characterizes the operation as a patch rather than a full replace, which lets an agent distinguish it from wave_create_estimate and wave_clone_estimate. It does not explicitly differentiate from wave_update_estimate_deposit, which is the closest ambiguity among siblings.

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?

Usage is implied rather than stated: 'Change an estimate' plus the note that omitted fields are copied from the current estimate tells the agent this is an incremental partial update. There is no explicit when-to-use/when-not-to-use framing and no mention of sibling alternatives such as the deposit-specific updater, so an agent must infer routing.

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