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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description adds substantial behavior beyond them: ambiguity and not-found return shapes, the needs_layout path, the rule that par/slope/meters are always for the named layout and tee rather than course headers, that tee_color must never be guessed, and that price.green_fee is usually null and should be sourced via web_fetch from course.website.

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?

Content is front-loaded with the return inventory before the usage rules, and nearly every clause carries operational meaning. It is a dense single block, though, and the media/app_links/green_fee tail is less critical than the earlier routing rules, so it could be trimmed or split for scannability.

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?

There is no output schema, so the description carries the return-value burden — and it does, naming found, candidates, needs_layout, media, app_links, price.green_fee and the per-layout/tee structure. For a 5-parameter, zero-required lookup tool, an agent has everything needed to call it and interpret edge responses.

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 baseline is 3; the description earns more by explaining that name accepts free-form player phrasing ('la Herrería', 'el Race'), that tee_color (with gender when both exist) is required for hole-by-hole meters, and that course_id comes from a prior call. It stops short of clarifying layout precedence versus the player's last round, which is only hinted at.

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 concrete inventory of what the card contains (pares, stroke index, barras con slope/course rating/metros por recorrido, hoyos clave, diseñador, web, teléfono, historial propio) — a specific verb+resource that an agent can match to a request without opening the schema. It also names the sibling tools it is not (get_course_plan, get_hole_plan) and the field it hands off (course_id).

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?

Explicit trigger conditions are given ('Llámala SIEMPRE que el jugador nombre su campo... o pregunte por un par, un slope, las barras, los metros'), plus explicit routing away to get_course_plan/get_hole_plan for attack plans. It even covers edge flows: no-argument default course, ambiguous names returning candidates, not-found returning found=false, and multi-layout clubs returning needs_layout.

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