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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description contributes genuinely non-obvious behavior: the pay-per-call model ($0.002 USDC via x402 on Base, Solana or Arc) and, importantly, that failed calls are not charged. Rate limits and result ordering are not addressed.

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, front-loaded with what the tool returns, then the domain constraints (leagues, season encoding), then the billing terms. Every clause carries information an agent needs, with no filler or restatement of the name.

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?

For a three-parameter, optional-arg lookup with a full output schema, this covers scope, valid values, season encoding and cost. It does not say how 'top players' is ordered (by xG presumably) or whether the count is capped at the limit, which is the main remaining ambiguity.

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 baseline is 3, but the description adds meaning the schema does not: it clarifies that season is the start year with a concrete mapping (2025 = 2025-26) and repeats the league vocabulary inline so the agent can validate arguments without opening the schema. The limit parameter is left entirely to 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?

States a specific verb and resource: Understat xG player stats for one league and season, and enumerates the exact metrics returned (goals, xG, xA, shots, key passes, minutes). It does not explicitly contrast itself with close siblings like dev_fbref or dev_fpl_premier_league, so an agent must infer that this is the Understat-sourced xG feed, but the branding and metric list make the intent unambiguous.

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 phrase 'for one league and season' implies the one-league-per-call scoping, and the supported league list bounds usage. However, there is no explicit when-to-use guidance, no mention of when to prefer this over dev_fbref/sofascore for the same question, and no prerequisites stated.

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