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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's job is to add behavior — and it does: it discloses the returned content, notes that odds are only given 'where measured', and that picks may be 'held at WATCH'. The explicit inclusion of 'what the model does not account for' sets useful expectations about caveats, though it doesn't address failure modes like a player with no published call.

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, the first front-loading the resource and enumerating the payload, the second giving usage triggers. The enumeration is list-heavy but every item describes a distinct returned field, so it earns its place; only the lack of a clear when-not clause keeps it from 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?

With no output schema, the description carries the burden of describing the return and does so thoroughly (tier, calibrated odds, projection vs threshold, WATCH reasoning, model limitations). It also states the NFL-only, this-week scope. Missing only behavior when no call exists or when line/stat matches nothing.

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 schema already explains player, stat, and line, including the 'defaults to the player's strongest published call' behavior. The description reinforces the single-call scope ('one NFL player prop this week') but adds no syntax, format, or disambiguation detail beyond the schema — baseline 3.

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?

The description names a specific resource and scope: the rationale behind one published NFL player-prop call, including contract, YES/NO call, Kalshi price, tier, projection vs threshold, and WATCH status. This is clearly distinguishable from siblings like explain_player, explain_game, nfl_prop_board, or track_record 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?

It gives concrete trigger phrasings ("why do you like <player>'s over", "explain the <player> prop"), which is stronger than generic guidance. However, it never names an alternative or exclusion (e.g., use nfl_prop_board to browse props or explain_player for a player-level summary), so routing to siblings is left implicit.

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