evaluate_trade

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

Annotations already declare readOnlyHint=true and readOnly safe semantics, and the description does enumerate the analysis outputs (deltas, forced drops, verdict), adding context beyond annotations. However, it doesn't state assumptions (roster state, league settings) or how names are resolved, and the parenthetical 'season-level' only lightly qualifies scope.

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 purpose and output list, but the run-on structure combining a long output inventory with a terse input note is dense and the input guidance is buried at the end.

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?

No output schema and zero param documentation means the description must carry the input contracts; it covers give/get format but omits partner semantics and doesn't clarify how the per-week/verdict outputs are produced or what inputs they rely on.

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 0% – none of the three required params (partner, give, get) are described in the schema. The description only says give/get are 'comma-separated names' and leaves 'partner' undefined entirely (is it a manager name? team id?), a substantial gap given zero schema help.

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?

Clearly states it evaluates a trade for both sides at season level, listing the concrete outputs (category per-week expectations, win-rate deltas, G deltas, forced drops/FA fills, verdict). Distinguishable from find_trades (discovery) and evaluate_add_drop (single-player), though it doesn't explicitly name those siblings.

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?

Implied use is when assessing a proposed trade, and the 'give/get' instruction hints at input format, but there is no explicit when-to-use vs find_trades or proposal_steps, and no stated preconditions.

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