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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds meaningful behavior beyond them: abandoned rounds only appear if they have played holes, source='garmin' narrows results to watch rounds, and shots_complete=false is explained as missing hole scores rather than rounds not played. It still says nothing about result ordering or what limit defaults to, which matters for a capped list.

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?

Purpose and status are front-loaded, and nearly every clause carries new information (visibility rules, source meanings, rescuable semantics). It is a single dense paragraph with stacked parentheticals, so it reads as run-on even though little is actually wasted.

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?

With no output schema the description must carry return-value meaning, and it does explain key returned fields (source, shots_complete, rescuable, rfeg_round_id). Given the tool's complexity, ordering, default limit, and the shape of the remaining round fields are the notable omissions.

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 baseline is 3, but the description genuinely enriches the enums: garmin means GPS shot-by-shot import with putts not always recorded, app means logged in Morris Golf, scan means a scanned paper card. It also explains that include_rfeg pulls official federation rounds carrying the rfeg_round_id needed downstream, adding value over the schema text.

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?

Specific verb+resource with domain detail: it lists the player's rounds along with their state (in_progress, completed, abandoned) and enumerates the origins each round may come from. The use-case framing ("to find the one to correct, close or rescue, or to see where each came from") steers the agent well, but it never names the closely related siblings such as get_round_history or get_round_card, so the boundary with those tools is left implicit.

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?

It gives an explicit when: when you need to locate a round to correct, close, or rescue, or to inspect its provenance, and it names the follow-up tools (reopen_round for rescuable=true, save_rfeg_pro_stats for include_rfeg rounds). There is no explicit when-not (e.g. "for a single round's card use get_round_card"), so alternatives among the list/detail siblings are only implied.

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