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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds nothing behavioral beyond that: it never says whether the original plan is mutated in place or a new derived plan is produced, whether team_id is required for authorization, or what constraints (e.g., week ranges) apply. "Adapts" is ambiguous about mutation semantics, which is exactly the gap an agent needs filled for a write tool.

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?

Two short sentences, front-loaded with the action and followed by the trigger; nothing is padded or redundant. The brevity is appropriate in form, though it is brevity purchased at the cost of specification rather than earned through tight expression of complete information.

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 return values need not be described, and the annotations handle the safety profile. But for a mutation tool with 10 fully undocumented parameters, no statement of in-place vs. derived output, and no guidance on week-range or team scoping, an agent has too little to call it correctly without guessing.

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 0% across 10 parameters, so the schema provides type and enum information but no meaning. The only hint the description offers is "for a user profile," which loosely gestures at end_user_age, end_user_gender and end_user_fitness_levels without explaining them, and says nothing about min_weeks/max_weeks interaction or user_requirements. This is a substantial shortfall given the parameter count.

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 states a specific verb and resource ("Adapts an existing program") plus a scope ("for a user profile"), which is clearly distinguishable from siblings like adapt_workout or generate_program by the word "program." It stops short of explicitly contrasting itself with adapt_workout, which adapts a single workout rather than a whole program, so an agent must infer the boundary.

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 when the user wants to customize a program" gives a positive trigger condition, but it names no alternatives and no exclusions. An agent cannot tell from this whether to prefer adapt_plan over update_program (edit in place) or generate_program (build fresh) when a user asks to 'change my program.'

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