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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is added context — and it delivers: data provenance (shift charts), a cross-validation against play-by-play, a season coverage window (2010-11 onward), and a concrete cost model (10 credits per game, multiplied when using date).

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?

Front-loaded with the core use case and packed with substantive detail — strength states, splits, provenance, cost, coverage window. It is a single long run-on sentence with mild redundancy ("every other on-ice state" after the exhaustive list), but nearly every clause carries information an agent needs.

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 derived-aggregate tool with an output schema and three optional params, this covers everything that matters: what is measured, where it comes from, how far back the data goes, what the optional flag adds, and what it costs. Return-value shape is correctly left to the output schema.

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 date, game_id, and include_players are already fully documented in the schema, including the default for include_players. The description mostly restates those semantics; the only genuine addition is the cost implication of the date parameter fanning out across every game that day.

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 resource with unusual precision: seconds per team by on-ice strength state (5v5, 5v4, 4v5, 4v4, 6v5, plus all other states), split regulation/overtime, sourced from shift charts. The enumeration makes it unmistakable against siblings like get_shifts (raw shifts) or get_game_detail (game-level summary), even without naming them.

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?

"Use for exact time at each strength" plus "from the shift charts" gives clear selection context, and it states the game_id-vs-date choice with per-call credit costs. It stops short of naming an alternative tool or an explicit when-not-to-use case (e.g. use get_shifts for raw shift rows), so it lands at 4 rather than 5.

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