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

The description discloses a key behavioral trait beyond the annotations: 'Every path in the mask also writes USER provenance, so correcting a carried-over value re-attributes it.' This is valuable context about side effects that the agent wouldn't know from the schema or annotations. The annotations only indicate openWorldHint=false and destructiveHint=false, so the description adds meaningful behavioral information about provenance re-attribution.

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 two sentences, both informative. The first sentence states the core operation, and the second adds a critical behavioral caveat. No wasted words, though the second sentence could be slightly clearer about the provenance implication.

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?

The tool has a complex nested schema and an output schema, so the description doesn't need to explain return values. However, it doesn't mention important context like whether the application must exist, whether partial updates are allowed, or how the updateMask interacts with the application object's nested fields. The provenance side-effect is disclosed, which is good, but the description could be more complete about the update semantics.

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 50%, with the 'application' parameter having a rich nested schema but no top-level description, and 'updateMask' having only 'Comma-separated field paths.' The description adds some context about the updateMask semantics (every path writes USER provenance), but doesn't explain the format of field paths or how they map to the application object. The schema itself provides detailed field descriptions for nested properties, so the description doesn't need to repeat those, but it could clarify the updateMask format more.

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') and resource ('Banking Application'), and the first sentence clearly indicates the operation: updating a banking application with a field mask. However, it doesn't explicitly distinguish this from sibling tools like banking_start_banking_application or banking_submit_banking_application, though the update semantics are reasonably clear from the name and description.

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 usage context: it's for updating an existing banking application using a field mask. It doesn't explicitly state when to use this tool versus alternatives like banking_start_banking_application or banking_submit_banking_application, nor does it mention prerequisites like the application needing to exist or be in a certain state. The field mask mechanism is mentioned but not explained in terms of when to use it.

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