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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral detail beyond that: what each view actually returns (all routines plus the active one, template metadata vs 'the full prescription with element ids, coach_note, superset groups and version'), which is valuable since there is no output schema.

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?

A single dense paragraph using '·' separators, front-loaded with the scope and then per-view detail; essentially every clause carries information. The packing makes it slightly harder to scan than separate sentences would, but nothing is 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?

For an 8-parameter, five-mode tool with no output schema, the description covers the essential decision inputs: mode selection, required ids per mode, and the shape of each return. Minor gaps remain (defaults, id stability, pagination/limits), but nothing needed to invoke it correctly is missing.

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 only 38% (equipment, split_type, fitness_level and include_templates carry no schema description), but the description compensates by naming exactly which parameters drive each view — split_type/frequency/equipment/fitness_level for seed_templates, routine_id for routine, template_id for template, include_templates=false for metadata-only. It does not explain enum value meanings or the boolean default, so this is strong but not exhaustive.

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?

States a specific verb+resource (read routines and workout templates) and immediately distinguishes itself from the mutation sibling by naming save_plan as the tool for changes. An agent can tell what this tool returns and what it is not for without opening the schema.

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?

Each view is enumerated with its purpose, which effectively tells the agent which mode to pick for which need, and 'Change them with save_plan' explicitly routes write intent to the alternative. It stops short of task-level triggers or exclusions (e.g. relation to read_workouts / live_workout state), so it is clear context rather than a complete when/when-not matrix.

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