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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the optimistic-concurrency SyncToken requirement and the fact that the saved record plus a new SyncToken are returned. It does not, however, restate or expand on the destructive/sparse-update semantics that live in the schema.

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 tightly written sentences with the operation and its key prerequisite front-loaded and the return value trailing. No filler, though the parenthetical about SyncToken is slightly wordy.

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?

There is no output schema, so the description earns credit for stating what is returned ('the saved record with its new SyncToken'). Combined with the rich entity schema, an agent has enough to invoke this mutation correctly; only the lack of alternative-tool routing keeps it from a 5.

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% and both parameters (entity, company) are thoroughly documented inline, including sparse-update behavior and the Active:false retirement pattern. The description only echoes Id/SyncToken, which the schema already defines, so it adds no meaning beyond the structured fields — baseline 3.

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 and resource ('Update an existing department in QuickBooks Online'), which clearly distinguishes it from create_department, get_department, and search_departments. It doesn't explicitly name those siblings, but the purpose is unambiguous for an agent scanning the tool list.

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?

Implies when to use it ('an existing department') and gives a concrete prerequisite ('fetch the Department first' to get the current SyncToken), but never states when-not to use it or points to alternatives like create_department for new records. Usage is inferable rather than explicit.

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