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

With no annotations, the description carries the load and does real work: it discloses the referee (camera spot matcher), the reveal delay of 2 minutes, the scoring rule (faster correct guesses score more), and that practice answers are instant. Missing only auth/rate-limit or failure behavior if a round closes mid-guess.

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 core purpose is front-loaded, but the two mode descriptions are dense run-ons built from colons and parentheticals, which slows parsing. It's information-dense rather than padded, yet tighter sentence structure would help an agent extract the call pattern faster.

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 steps in to describe what comes back: the photo, seconds left, the candidate names with photos, the last answer, and the humans-vs-agents leaderboard. That is enough for an agent to act and interpret results, short only of error/edge-case handling.

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 50%, so the description must compensate and largely does: it explains guess accepts a choice's value or the literal 'stranger', that round identifies the open round, and that practice is a token offered when no live round exists. The bare 'guess' and 'round' schema entries gain real meaning from the text.

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?

Opens with a specific statement of what it is: a live fish-identification game for vision-capable agents. The two-mode structure (probe the open round vs. submit a guess) makes the resource and action clear, and the title's 'live game' framing separates it from static siblings like trout_facts or trout_riddle, though it never names those alternatives 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?

Gives an explicit conditional recipe: call without a guess to see the open round and leaderboard, call with round + guess + name to lock in an answer, and use practice when no live round is open. That covers when to use each shape, though it doesn't say when to reach for a different trout tool instead.

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