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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial context: the data capture window (once, in the final 75 minutes pre-kickoff), the cohort of 3-6 books, the per-line over/under shape, a 10-credit cost, and an explicit safety policy against computing stakes or recommending bets. Nothing essential is left for the agent to discover by trial.

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?

Well front-loaded: purpose, then inputs, then return shape, then availability caveats, then routing and cost/usage policy. Dense but every sentence carries information. It runs long, and the market list partially duplicates the enum, which keeps it just short of a 5.

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?

Despite an output schema being present, the description still tells the agent what a row looks like (per line, the over price, and the under where posted) and when the dataset will be empty. Combined with the cost and the no-advice policy, an agent has everything needed to call it correctly and interpret an empty result.

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 enum meanings, game_id format, bookmaker key, and estimate_only are already documented. The description echoes the player_id sourcing ('a GSIS id from search_players') and the required game_id/market but adds no syntax or format detail beyond that. Baseline 3 applies when the schema carries the parameter burden.

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 verb ('Use for') plus the resource ('alternate player prop lines by sportsbook') and immediately scopes it: 'every line a book posted for a player in one game, not only the main one', with a concrete example ladder. An agent can distinguish it from get_player_props and get_prop_history without opening any 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?

Explicitly names the alternatives and the condition that selects each: get_player_props for the main line and opening/closing prices, get_prop_history for how a player did against his main line. It also states the availability boundary (NFL 2023+, last 75 minutes before kickoff, 3-6 books, none for games further out) so the agent can decide when the tool will return data at all.

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