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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes beyond them with 'Never stored, never counts' and the frozen-practice-data note — the most decision-relevant fact (this trial has no ranking consequences). It stops short of describing response shape or any rate/eligibility limits beyond the signed-off-league restriction.

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?

Dense but front-loaded: the core purpose comes first, then the two-mode behavior, then the guarantees. The telegraphic style ('Never stored, never counts') is efficient, though the middle sentence is long and packed with clauses.

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?

With no output schema, the description steps in to describe what each mode returns (the practice task file with frozen data plus tasks; instant scoring with expected answers). That covers the essential unknowns for a two-mode read tool, leaving only minor gaps like task_id format details.

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?

With only 50% schema description coverage, the description carries the load: it explains that 'answers' is a {task_id: answer} map whose omission changes the tool's behavior entirely, and it constrains 'league' to signed-off task leagues. The enum values themselves are self-describing, so little is lost.

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 specific verb and resource ('try a league') plus the two distinct modes (fetch practice tasks vs. score submitted answers), which lets an agent distinguish it from arena_submit_answers and arena_round_tasks. The 'no sign-up' qualifier further separates it from the ranked-round siblings.

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 clearly frames when to use each mode ('without answers' vs. 'with answers') and gives the governing constraint 'Signed-off task leagues only'. It does not, however, explicitly name the alternative tools (e.g., arena_submit_answers for ranked play), so routing is implied rather than stated.

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