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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context — plan-tier caps on game count and the 7-day window on per-game rows — but leaves unclear what "graded" means (settled vs. pending), what the tier field actually counts, and, with no output schema, what the returned hit-rate rows look like.

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 short sentences, front-loaded with the core definition, with the plan restriction appended as a secondary qualifier. Nothing is padded, though the extreme brevity leaves real gaps that a slightly longer description could close.

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 7-parameter, single-required stats tool with no output schema, the description covers what is computed and the free-plan limitation, which is the most important operational fact. It does not explain the more/demon/goblin tier semantics, how league affects results, or what the response contains, leaving meaningful work to the agent's inference.

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 description coverage is 100%, so the schema fully documents last, stat, tier, league, player/player_id and user_request; the baseline is 3. The description does add one constraint not visible in the schema — that the free plan effectively caps results at the last 10 games — which clarifies the practical ceiling of the `last` parameter (schema allows up to 100).

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?

"How often one player has gone over, per stat, across their last graded games" gives a specific verb-like computation (over-rate frequency), a scope (single player, per stat, last graded games), so an agent knows this is a hit-rate aggregation rather than a raw log. It does not, however, distinguish itself from plausible siblings such as get_game_logs or get_projections, which could return overlapping underlying 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?

The description gives no when-to-use guidance and names no alternative tool, so an agent must infer that this is the right call for over-rate questions versus get_game_logs for raw results. The only usage-adjacent content is the plan constraint (free plan = last 10 games, per-game rows from last 7 days), which is a limitation rather than a routing rule.

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