start_application

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

With no annotations provided, the description carries the full burden and does well by disclosing the preflight checks (dedup gate, daily cap), the return of a step plan, and the exclusion of submit steps. However, it doesn't mention potential side effects on state (e.g., whether a session is created or if any record is marked) or what happens on preflight failure.

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 long, front-loaded with the core purpose, and every clause adds value. It flows well and contains no redundant 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?

Given that an output schema exists, the description doesn't need to detail the response format, but it covers the key execution context: preflight steps, the step plan, the exclusion of submission, and the human-in-the-loop requirement. It could mention error handling or prerequisites (e.g., calling after approve_match), but overall it's sufficiently complete for the task.

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 0%, so the description must compensate, but it only implies that 'finding_id' refers to an approved match without explicitly defining the parameter. The context gives some hint, but it doesn't clearly state the format, source, or validation rules for finding_id.

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 with a specific verb ('start') and resource ('supervised application session'), explicitly scoped to 'APPROVED match'. It also distinguishes itself from the sibling tool 'request_submit' by clarifying that the returned plan never contains a submit step.

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 explicit when-to-use guidance ('for an APPROVED match') and explicitly names the alternative submission route ('request_submit is the only submission route'). It also implies that the agent should execute the step plan in the user's browser, providing clear operational context.

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