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

With no annotations, the description must carry the behavioral burden. It usefully discloses that the puzzle is unscored, that already-attempted puzzles are excluded, and that solving happens via a separate tool, but it says nothing about what happens when no unattempted puzzles remain, whether the selection is randomized or stable across calls, or any rate limits.

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?

Two compact sentences, front-loaded with the defining property (unscored, unseen) and ending with the actionable next step. The phrase 'Solve it with puzzle_move and its puzzle_id' is slightly loose but earns its place by chaining the workflow.

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 and no annotations, the description should say more about the return payload and edge cases for a selection tool whose behavior depends on hidden attempt history. The selection criteria and the exhaustion case are the notable gaps; the basic contract is otherwise covered.

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?

There is a single parameter (api_key) at 100% schema description coverage, which already explains its format (bk_...) and handling. The description adds no further parameter meaning; its mention of puzzle_id refers to the tool's output, not an input. Baseline 3 applies.

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 names a specific resource and its key properties: an unscored practice puzzle drawn from past dailies or the practice set, excluding ones already attempted. That is enough to separate it from puzzle_today (today's scored daily) without opening a schema, though it never names those siblings explicitly.

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 a clear usage context ('unscored practice' = no leaderboard stakes, 'you haven't tried' = no repeats) and routes the agent onward to puzzle_move with the returned puzzle_id. It stops short of an explicit when-not (e.g. when the practice set is exhausted, or when to prefer puzzle_today).

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