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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description goes well beyond that: it discloses the data lineage ('built from play-by-play'), the concrete consequence that time on ice and plus/minus come back null, the goalie-specific caveat that time on ice exists only for started games, and a cost signal ('Costs 5 credits'). This is exactly the kind of non-obvious behavior an agent needs before calling.

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?

Three tight sentences, no filler: the use condition and the skater/goalie field lists come first, the null caveats follow, and the prerequisite plus cost land last. Each sentence carries distinct information an agent would otherwise have to infer.

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?

An output schema exists so return structure needn't be spelled out, yet the description still flags which fields will be null and why, which is the one thing the output schema cannot express. For a read-only, six-parameter tool with full schema coverage, nothing needed to invoke it correctly is missing.

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%, with limit, league, offset, season and game_type all self-documented including defaults, so the schema carries the parameter burden and baseline 3 applies. The description only adds a prerequisite for player_id (from search_players) and notes the resolved season is echoed back, without adding format or syntax detail for the remaining parameters.

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 verb+resource ('a player's game-by-game stat lines for a season') and immediately contrasts with what it is not ('not a season total'), which cleanly separates it from get_player_stats/get_skater_season_stats. It also enumerates the exact fields returned for skaters vs goalies, so an agent knows the granularity without opening a schema.

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 use condition ('Use when you need a player's game-by-game stat lines for a season') and an implicit exclusion ('not a season total'), plus the prerequisite 'Requires player ID from search_players'. It stops short of naming the alternative tool (e.g. get_player_stats) outright, so routing relies on the agent recognizing the season-total counterpart by description.

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