Evaluate a Champions VGC team

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

Annotations only declare destructiveHint=false, leaving the description to carry the behavioral burden. It adds genuinely useful disclosure: scores are 'pressure heuristics' (so the agent should not treat them as exact win probabilities) and comparisons run on 'identical sources and conditions' (controlling for confounding variables). It could go further — e.g., whether profile_id is needed, whether evaluation_context is required for meaningful results — but it adds real context beyond the single annotation.

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 and roughly 30 words, with the primary function front-loaded and the comparison option and heuristic caveat placed second. There is no wasted text, but the density of unexplained jargon means each sentence does not earn its place in clarity as well as it could.

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?

This is a complex tool — 4 parameters, nested evaluation_context object with modes/roles/priorityThreats, zero schema description coverage, and only destructiveHint in annotations — yet it gets just two sentences. The description never explains what team_export should contain (e.g., Pokemon Showdown format), what profile_id is for, or how modes with bringFour/lead/mega/targets are structured. The output schema mitigates the return-value side, but input construction is critically under-specified.

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?

With schema description coverage at 0%, the description must compensate by mapping to parameters, and it does so only obliquely: 'Mega alternatives' hints at modes[].mega, 'threat-aware cohort' hints at priorityThreats, and 'compare an edited team' maps to comparison_team_export. The required team_export, profile_id, and the roles object are never mentioned, so the agent gets no help constructing the most important input or the evaluation_context structure.

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?

States a clear verb+resource: the tool evaluates a VGC team, specifically 'legal Mega alternatives' and 'fixed matchup modes', and adds an optional comparison mode. It is distinguishable from sibling tools (none of which evaluate teams — they analyze replays, query meta, calculate damage). However, the heavy jargon ('legal Mega alternatives', 'fixed matchup modes', 'threat-aware cohort') is never unpacked, so an agent without VGC domain knowledge gets only a fuzzy picture of what actually happens.

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?

The second sentence gives one concrete usage scenario — comparing an edited team on 'identical sources and conditions' — which implies the tool's role as a controlled evaluator rather than an open-ended analyzer. But there is no explicit routing among the nine siblings: no 'use this instead of vgc_matchup_detail when...' or 'not for replay-level analysis' type exclusions.

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