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

Annotations already establish readOnly, idempotent, closed-world, but the description adds real value on top: the two operating modes (live round vs hypothetical course), what the response reports (gross and net stroke advantage over shared holes, holes won and lost), and that ghost selection lives in the app rather than in this call. Nothing contradicts the annotations. It stops short of detailing edge cases like missing shared holes or what happens if the player has no qualifying card.

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?

The core concept is front-loaded in the first sentence, and each clause carries information rather than filler. The downside is density: long run-on sentences with nested parentheticals make it harder to scan than a split definition of concept, modes, and returns would be.

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 the return-value burden, and it does describe what the duel reports (gross/net stroke deltas, holes won and lost). For a five-parameter, all-optional tool whose domain concept is non-obvious, this is close to complete; only edge-case behavior and the exact response shape are left implicit.

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 description coverage is 100%, so the schema already explains tee, mode, segment, round_id and course_id individually. The description contributes the interaction between them (round_id defaults to the round in play; course_id plus segment and tee produces a hypothetical matchup) and glosses mode as best-clean-card vs. recent average, but adds no format or constraint detail beyond the schema. Baseline 3 with modest added relational meaning.

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 defines a specific resource ('el duelo fantasma') with a clear verb ('get') and unpacks what the ghost actually is: the player's own best clean card on a course/tee or their recent hole-by-hole average. It goes well beyond the title, which says nothing. It does not explicitly distinguish itself from nearby siblings such as get_round_card or get_round_insights, which keeps it at 4 rather than 5.

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?

Usage is condition-driven and explicit: without round_id it reads the round in play, with course_id (plus segment and tee) it answers which rival would exist on that course. It also clarifies that this tool only queries the ghost ('desde el chat se consulta y se cuenta') while the player chooses it in the app, which implicitly warns the agent not to expect selection here. No named alternative tools, so not a 5.

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