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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: results are ordered, historical matches have reduced coverage, and each call costs 10 credits — the cost disclosure is exactly the kind of thing annotations cannot express.

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 purpose, then filtering, then the coverage caveat, then cost — a sensible information order in three tight sentences. The long enumeration of event fields is dense but earns its place by previewing the payload.

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 return-shape explanation is rightly omitted; the description instead covers ordering, historical coverage limits, and credit cost for a 5-param read tool. The only real gap is the mismatch between described event types (corners, offsides) and the kind enum values, which could mislead filtering.

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 enum and defaults for kind, limit, league and offset are already documented; the description's "Filter with kind" adds little beyond that. Worse, it lists "corners, offsides" as event types while the kind enum only offers set_pieces/fouls/goals/shots/cards/substitutions/all, so an agent could infer a non-existent filter value.

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 and scope: "Use for a match's events in order," then enumerates exactly which event types are returned (goals with assister/own goals/penalties, shots with location/outcome/body part/xG, cards, subs, fouls, corners, offsides, VAR). An agent can tell this is the match-event feed rather than a stats or shot-map tool, though no sibling is named explicitly.

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?

"Use for a match's events" plus "Filter with kind" gives clear context for when this applies, and the older-match caveat ("Older matches carry goals, cards and substitutions only") tells the agent when results will be thin. It stops short of naming alternatives (e.g., get_shot_map for shot visualizations) or stating exclusions.

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