get_teamplay_report

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

With no annotations, the description carries the full burden, and it does disclose real behavioral substance: concrete thresholds for death buckets (<15m, 15-25m, >25m) and the 5s kill-after-teammate-death trade window, which define what the analysis actually computes. What it omits is operational context — that it is a read-only, potentially slow multi-match aggregation and roughly how much data is scanned by default.

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?

The metric list is front-loaded in scannable bullets and each bullet contributes a distinct analysis dimension rather than restating the previous one. The opening fragment is slightly clipped and a couple of bullets are long, but nothing is wasted.

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 the description need not explain return shapes, and the schema fully documents the seven parameters. The remaining gap for an annotation-free analysis tool is the absence of any statement about cost, data volume, or read-only nature, but the analytical content itself is complete.

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%, including the enum for mode, the semantics of season overriding count, and the Riot ID format, so the schema already documents every parameter. The prose adds nothing parameter-specific beyond the implicit framing of what is being analyzed, making the baseline 3 correct.

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 opens with a specific verb-and-resource framing ('Spacing and trading, from every player's position at each kill') and then enumerates the exact analytics produced: distance-bucketed deaths, trade rates, isolated-death map spots, and party-size win rates. This is far more specific than any sibling could be, and an agent can immediately tell this apart from get_performance_report or get_match_history.

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 explicitly maps three natural-language intents to the tool ('why do I die alone', 'am I trading my teammates', 'who should I queue with'), which is strong routing guidance. It stops short of naming alternatives or exclusions (e.g., that pure aim/score trends belong in get_performance_report), leaving the agent to infer the boundary against eight siblings.

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