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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so much of the safety profile is free. The description's genuine addition is the cost disclosure ('5 credits'), which is real, actionable context beyond structured fields. It still omits anything about payload size or latency, which matters for a tool returning bio, rankings, ratings, career records, and 10 matches in one response.

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-loading is good — the purpose statement comes first and the cost last. But the middle is a semicolon-chained inventory of return fields that duplicates what the output schema already conveys, and the tour/league sentences are ambiguous enough to require a second read. It is dense rather than tight.

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 needn't explain return shape, and the credit cost plus the player_id/league guidance cover the practical call requirements. The remaining gap is sibling positioning against get_player_stats, get_ratings, and get_surface_splits, whose outputs this tool appears to bundle. That omission is the main thing an agent would still have to guess.

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%, both parameters are documented, and player_id's provenance ('from search_players') is already in the schema, so baseline is 3. The description's tour/league paragraph actually reduces clarity: it describes an 'atp (default) or wta' tour concept, then instructs passing league: "wta" on a shared endpoint, while the schema enum is tennis/wta defaulting to tennis — an agent has to reconcile 'atp' with 'tennis' on its own.

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-plus-resource framing ('Use for a player profile') and then enumerates exactly what is returned: bio, latest ranking, ratings per surface with peak, career records, titles, and last 10 matches. That is far more concrete than the title 'Player'. It does not, however, distinguish this aggregate profile from overlapping siblings like get_player_stats, get_ratings, or get_surface_splits, so the agent can't tell from the text alone whether those are subsets or complements.

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 player profile' gives an implied trigger, and 'Costs 5 credits' hints this is the heavier, broader call. But there is no explicit when-not, no mention of which sibling to prefer for just stats or just ratings, and the tour/league note reads as a usage instruction yet conflicts with the schema's enum. Usage is inferable, not stated.

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