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

Annotations already cover read-only, idempotent, non-destructive, open-world. The description adds substantial behavioral context beyond that: model limitation ('no OOS/independence gate'), quality warning ('reliability is emerging on v0'), cost behavior ('1 credit; empty slate is still 200'), and data-source constraints ('soft-book game-unit lines only, never Pinnacle's set-unit total'). No contradiction with the annotations — 'a prediction' aligns with readOnlyHint.

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?

On the longer side, but front-loaded: the first sentence states purpose and the key caveat. Every sentence earns its place (scope, tennis specifics, output fields, routing, cost, docs). The conviction formula is borderline detail but aids output interpretation, and the doc links provide an escape hatch. Slightly dense, not padded.

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 an output schema present and full safety annotations, the description covers everything an agent needs to call correctly: scope, sports, market mappings, model caveats, cost, empty-slate behavior, and two doc links for field catalog and worked examples. Nothing material is missing for a read-only listing tool.

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 baseline is 3. The description adds genuine meaning beyond it: it maps the market enum to concrete tennis bet types (ML_P1/ML_P2 for h2h, SPREAD_P1/SPREAD_P2 for spreads, OVER/UNDER for totals) and explains the underlying models (rate model for props, ranking Bradley-Terry, Normal-aproximated games). This helps an agent choose correct sport/market combinations, though the basics are already in the schema.

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+resource: 'Daily board of forecasted wagers from Lumify's model'. It immediately distinguishes itself from list_ev by explicitly stating it is a prediction, not a beat-the-market claim, and that list_ev is the gated main-line +EV claim. The scope (player props on six sports, tennis main-line bet types) further pins down exactly what this tool returns, so an agent cannot confuse it with siblings like get_odds or get_player_props.

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 routing rule: 'Use list_ev to scan main lines by sharp-fair price gap; use this tool to scan high-probability forecast'. It also names the exclusion condition ('no OOS/independence gate') and points to list_ev for the gated claim, so when-not-to-use is stated as clearly as when-to-use.

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