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

The annotations are generic (readOnly=false, destructiveHint=true), but the description/schema disclose substantial behavior: sparse updates by default, replacing lines with a Line array, sparse:false clearing omitted writable fields, replaying PaymentType and AccountRef on sparse updates, and prohibitions on sensitive identifiers. This goes well beyond what the annotations provide and there is no contradiction.

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 tool-level description is a single front-loaded sentence stating what the tool does and its key prerequisite. The more complex sparse-update details are correctly placed in the parameter schema where they belong, and every sentence earns its place with 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?

For an update tool with a nested object and destructive potential, the combined description and schema cover the prerequisites, mutation semantics, line-replacement behavior, field restrictions, and optional company selection. The absence of an explicit response shape is minor for invoking the tool, and the schema is rich enough that an agent can call this correctly.

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%; the entity parameter already documents Id, SyncToken, sparse semantics, and forbidden fields, and the company parameter is described as optional. The tool description adds only the brief 'requires Id and SyncToken' note, so it does not materially expand on the schema — the baseline 3 applies.

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 and resource: 'Update an existing purchase in QuickBooks Online.' The parenthetical 'requires Id and SyncToken' immediately distinguishes this from create/delete/search operations, and among the many sibling update_* tools the resource name and QuickBooks context make the target 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?

The description implies the right usage context by requiring an existing purchase with Id and SyncToken, and the schema says to fetch the Purchase first, which hints at get_purchase as a prerequisite. However, it never explicitly names alternatives such as create_purchase for new purchases or states when not to use this tool, so the routing guidance is implied rather than direct.

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