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

Annotations already signal destructiveHint=true, but the description adds meaningful behavior beyond that: sparse updates avoid clobbering, full updates clear omitted writable fields, read-only preference fields are rejected, and a current SyncToken is required. This is exactly the behavioral context an agent needs before mutating company preferences.

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 sentences with no filler: the first front-loads the purpose and the critical payload requirements, the second adds the key field-level constraint. Detailed rules are correctly deferred to the schema rather than bloating the description.

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 destructive update tool with rich schema coverage and annotations, this definition covers the full call cycle: obtain current Preferences for Id/SyncToken, send a sparse update, avoid read-only and sensitive fields, and understand full-update clearing behavior. The absence of an output schema is acceptable because the critical preconditions are thoroughly described.

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%, so the schema already documents entity and company, including sensitive-field prohibitions and sparse-vs-full semantics. The description adds explicit value by requiring sparse: true and warning that read-only fields are rejected, which helps the agent construct a valid payload. There is minor tension with the schema's 'sparse by default' phrasing, but the added guidance is still useful.

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 states a specific verb and resource: 'Update the company's QuickBooks preferences.' Among a large sibling set of update_* tools, it uniquely targets preferences and is clearly distinct from get_preferences. The sparse-payload requirement adds operational specificity without obscuring the purpose.

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 and entity schema give a clear invocation context: fetch Preferences first to obtain the current SyncToken, send a sparse payload, and avoid read-only or sensitive fields. It does not explicitly name get_preferences as the read alternative or list when-not-to-use conditions, but the prerequisites and sparse/full-update behavior are well conveyed.

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