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

Annotations only say this is a non-read-only, non-destructive call; the description adds far more: unanswered tasks score as unsafe, the run is sealed and published to the scoreboard, 80.0 is the certification threshold, and an X-API-Key header is required. These are non-obvious consequences an agent could not infer from the annotation flags.

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?

Purpose and argument shape are front-loaded, and the return format, sealing behavior, and auth requirement follow in a logical order with no filler sentences. The middle sentences are dense and pack several distinct concerns together, which slightly hurts scanability.

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 submission tool with no output schema, the description still describes the response shape (per-task results with instance_id, safe, critical, verdict plus a score) and the success threshold. Combined with the auth note and the unsafe-by-default rule, an agent has everything needed to call it correctly.

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 coverage is 100%, so the baseline is 3, but the description earns more by defining the otherwise opaque `decision` object — either a purchase shaped like a check submission without a mandate reference, or {"ask": true}. It also states the omission semantics of `answers`, which the schema does not. The agent_id and session_id parameters get no elaboration beyond the schema, so it is not a 5.

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?

States a concrete verb and resource: submit decisions for an open exam session and receive a score. It explicitly anchors to the sibling provecart_agent_exam_start as the prerequisite, so an agent can distinguish this terminal submit step from the session-start tool without reading either schema.

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?

It gives clear context: one entry per task from provecart_agent_exam_start, plus the explicit fallback condition for emitting {"ask": true} when the instruction does not settle the choice. It does not name a when-not-to-use case or what to do if the session is already sealed, so it stops short of a 5.

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