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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so safety needs no restating; the description instead adds the non-obvious cost signal ('Costs 2 credits') and the endpoint-dependent league quirk, which an agent cannot get from annotations. Returned content (players, seeds, score, sets with tiebreak points) is also disclosed, though pagination behavior is left to the schema.

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-loads the purpose, then the required identifiers, then filters, then the cost note — a sensible ordering with little filler. The tour/league sentence is the one dense, slightly ambiguous spot, but the description is not bloated.

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 brief field listing is sufficient rather than redundant. With annotations covering the safety profile and the schema covering pagination bounds, the description supplies the only pieces an agent needs on top of them: which scoping keys count, the date format, and the credit cost.

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 75%; the description adds genuine value by resolving the semantics of the format-sensitive fields — date is UTC, round takes values like "Final", status is a filter, and league must be "wta" when hitting the shared endpoint. It does not cover limit/offset defaults or max limits, which the schema handles. Minor friction: it mentions a 'tour' concept (atp/wta) that does not map cleanly onto the enum-constrained 'league' parameter.

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 ('match results by day, tournament or season') and enumerates the returned fields, so the agent knows exactly what it retrieves. It never names a sibling such as get_match (single match) or get_player_matches, so differentiation must be inferred from the 'by day/tournament/season' scoping.

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?

Gives concrete calling patterns: 'Pass a date (YYYY-MM-DD, UTC), a tournament_id or a season' plus optional round/status filters. It does not state when to prefer this over get_player_matches or get_match, and the 'Tour: atp (default) or wta; on the shared endpoint pass league: "wta"' sentence is somewhat cryptic about which endpoint you are on.

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