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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is largely covered by structured data. The description still adds real value by describing the shape of the returned artifact (day-by-day week with session length, blocks, intensity, tracking targets, and adjustment rules) and by disclosing that output adapts to training history. It stops short of stating determinism or how 'notes' (e.g. an injury mention) is handled internally.

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?

Well front-loaded: trigger condition first, then return shape, then exclusions, then prerequisite. Slightly over-long because the two negative sentences ('Do NOT use for injury rehabilitation...' and 'Do not use to prescribe a program for a condition the user has disclosed') overlap in intent and could be merged without losing meaning.

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 correctly takes on the return-value burden and does so concretely, and it supplies the prerequisite sequencing an agent needs before calling. What remains unstated is minor: whether the tool persists anything, and whether follow-up tools (e.g. fitness.build_fuel_plan) are expected after building the week.

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%, including enum meanings for goal, equipment, and sessionsAre, so the schema already carries the parameter burden and a 3 is the correct baseline. The description adds only loose mapping — 'their goal, a specific split, or their current session frequency' — and says nothing new about notes or the capacity distinctions in sessionsAre.

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 trigger verb and resource — building 'a week of training' — and enumerates the three inputs that shape it (goal, split, session frequency). It is clearly distinguishable from fitness.assess_performance_profile, which it explicitly casts as a prerequisite rather than an equivalent, and from the other fuel/progress siblings by scope.

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 explicit positive conditions ('when a user wants a week of training built around their goal...'), explicit negative conditions (injury rehab, post-surgical, return-from-injury, prescribing for a disclosed condition), and an ordering rule ('Use fitness.assess_performance_profile first when you have not yet seen the user's training history'). All three of when-to-use, when-not-to-use, and sequencing are present.

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