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

Annotations already flag destructiveHint=true, but the description adds substantial behavior beyond that: updates are sparse by default, sending a Line array replaces all lines, sparse:false clears every omitted writable field, and sensitive fields like SSNs and birth dates must be managed directly in QuickBooks. This is exactly the kind of destructive/behavioral detail an agent needs.

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 description is a single tight sentence that fronts the action, resource, system, and the key precondition, with zero filler. The more detailed behavioral and parameter information is appropriately delegated 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 with a nested object parameter and no output schema, the definition is nearly complete: it covers preconditions, sparse vs. full update behavior, line replacement, sensitive-field exclusions, and optional company selection. The remaining gap is that it never names the companion read tool for fetching CompanyInfo or states what the update call returns.

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%, so the baseline is 3. The entity parameter is richly documented in the schema, including Id/SyncToken requirements and sparse update semantics, and the company parameter is also explained. The tool description only restates the Id/SyncToken requirement already present in the schema, adding no new parameter-level meaning.

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 ('Update'), a specific resource ('existing company info'), and the target system ('QuickBooks Online'). The word 'existing' plus the Id/SyncToken requirement clearly distinguishes update from creation, but it does not explicitly differentiate from sibling read tools like get_company_info or search_company_infos.

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 schema make the prerequisite clear: fetch the CompanyInfo first and supply Id plus current SyncToken. It also tells the agent which fields must not be sent. However, it never names alternatives or states when-not-to-use conditions, so routing among the many company-related sibling tools is inferred rather than explicit.

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