submit_login_code

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

With no annotations provided, the description carries the burden. It discloses that codes are single-use and expire, and that a refusal means the login flow must be restarted. It also instructs the agent to 'keep a copy of the restored profile' – a behavioral directive beyond the tool's own action. It does not explicitly state that completing login mutates session state, but the output schema likely covers the result. This is solid disclosure for a simple auth tool.

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 no filler. The main action is front-loaded, followed by a critical behavioral note and a fallback instruction. Every sentence contributes essential 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 tool is simple with one parameter and an output schema. The description covers the action, the code's constraints, and the fallback. It doesn't explicitly state the prerequisite of having called start_login, but this is strongly implied by 'finish the login.' The instruction to keep a profile copy is an extra nuance that helps the agent. Given the output schema exists, the description is largely complete.

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?

The input schema already describes the code as 'The one-time code Ozon sent; digits only, as received' – 100% coverage. The description adds the expiry and single-use constraints, which are not in the schema, enhancing the agent's understanding of the parameter's lifecycle. This adds meaning beyond the schema, so it exceeds the baseline of 3.

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 opens with 'Finish the login with the code Ozon sent' – a specific verb (finish) and resource (login) that clearly states the tool's role. It distinguishes itself from start_login by describing the completion step, and the sibling list confirms start_login exists. The purpose is unambiguous.

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 explicitly names the alternative: 'if it is refused, call start_login() again.' This gives a clear condition and directs the agent to the correct fallback. It also implies this tool should be used after start_login, and the warning about code expiry and single-use adds context on when to retry.

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