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

Annotations declare destructiveHint=true, and the description adds important context beyond them: it returns the saved record with a new SyncToken, and the schema notes sparse-by-default updates, line replacement, full-update behavior, and retire-via-Active:false. The top-level description itself could state the mutation and SyncToken chaining more explicitly, but it is a genuine supplement to the annotations.

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 compact sentences, front-loaded with the action and the hard prerequisite, followed by the return value. 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?

Covers the mutation, the auth-like prerequisite (Id+SyncToken), and the return value for a destructive write tool with no output schema. It lacks explicit guidance on fetching the record beforehand via get_account and does not say what happens on stale SyncToken, leaving a small gap.

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% and the entity description already documents Id/SyncToken inclusion, sparse behavior, and the Name/AccountType repeat rule. The description only mentions the Id/SyncToken requirement, which the schema also states, so it adds little beyond the schema. 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?

States a specific verb+resource ('Update an existing account in QuickBooks Online') and distinguishes it from create_account and get_account via 'existing' and the SyncToken prerequisite. An agent can place it among the many update_* siblings 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?

Explains the precondition (requires Id and current SyncToken 'as the last search or write returned it'), which implicitly tells the agent to fetch first via get_account. However, it never explicitly names get_account or search_accounts as the alternative, nor when to prefer create_account vs this tool. Usage is implied rather than directed.

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