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

Annotations already establish readOnly and openWorld, so the safety bar is pre-cleared; the description adds substantive behavior beyond that: the response is a ~10 second frame window rather than a whole game, and frames start at the supplied timestamp. It says nothing about whether this works for finished games at scale, error behavior for an out-of-range timestamp, or freshness of the live feed.

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 sentences, front-loaded with the payload description, then the calling rules. The stat enumeration is long but dense and directly informs whether the tool answers the question, so every clause earns its place.

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 an output schema and 100% parameter coverage, the description needn't explain return values, and it correctly spends its words on windowing behavior and ID sourcing. The remaining gap is sibling positioning against lolesports_game_details and lolesports_live, which a caller selecting among LoL tools genuinely needs.

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 adds genuinely new semantics: it explains that omitting starting_time means different things for live games (latest window) vs. completed games, which the schema alone does not convey. Worth noting the schema text 'Omit for the game's first frames' conflicts with the description's 'omit for the latest window' on a live game — the description is the richer source but the discrepancy should be resolved.

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?

Specific verb and resource: 'Returns the live-stats window of one League of Legends game', followed by an enumeration of exactly what the payload contains (patch, team/player metadata, ~10s of frames with gold, kills, objectives, per-player stats). This is far more precise than the name alone. However, it never distinguishes itself from the close sibling lolesports_game_details, so an agent has to guess which one to call when it just wants match data.

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 explicit, branch-based guidance: omit starting_time for a live game's latest window, pass an in-game starting_time with seconds divisible by 10 for a completed game, and take game_id from lolesports_event. That covers when and how to use it well. It does not name an alternative tool to use instead when this one is wrong (e.g. game_details for a whole-game summary), so it falls 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.