Submit an approved application

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

Annotations already indicate destructive behavior, and the description adds that it runs submission guards and describes mode-specific actions (filling, clicking submit). However, it does not disclose what happens on guard failure or the irreversible nature of full auto submission beyond the annotation's generic destructive hint.

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?

Three sentences with zero fluff. The most important behavior (guard execution and mode outcomes) is front-loaded, and every sentence contributes unique information.

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 description covers mode logic well, but omits key context such as what happens when a guard fails, prerequisites (e.g., application must be approved), and any relevant return value or side effects. Given the tool's complexity and lack of output schema, more detail would be helpful.

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 already covers 4 of 6 parameters with descriptions. The tool description adds meaning to the 'mode' parameter by explaining each enum value, and implicitly references the verification gate for related parameters. However, it does not clarify applicationId or headless beyond schema constraints.

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 clearly states the tool's purpose: it runs every submission guard and then submits according to the selected mode. It distinguishes from siblings by detailing three specific modes (manual, assisted, auto) and the allowlist constraint for auto mode.

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 provides clear context for choosing a mode, but does not explicitly compare this tool with siblings like submit_batch or record_submission. It lacks guidance on when to use submit_application vs batch alternatives, leaving the selection partially implicit.

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