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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds that the exercise runs in-chat at fixed durations and auto-selects a pattern — useful behavior beyond annotations — but never says what the agent receives back or whether it should narrate the exercise, which matters for a tool whose output has no 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?

Well front-loaded with the core action and duration first. The middle sentence is a long, comma-spliced catalogue of scenarios that borders on redundancy ('stress, anxiety or overwhelm... frustration or feeling stuck... low energy or burnout') and could be compressed into a few categories without losing signal.

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 a simple, read-only, zero-required-parameter action with no output schema, the description covers purpose, duration limits, and pattern selection well. The remaining gap is what happens after invocation — whether the chat takes over or the agent must drive the exercise — but that is a minor omission for a tool of this complexity.

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 33% (only 'feeling' is documented in-schema), so the description partly compensates: it surfaces the 1/2/5-minute options and the feeling-to-pattern selection logic ('Picks the pattern from how the user feels unless one is named'). However, the four pattern enum values (cyclic-sighing, box, 4-7-8, coherent) are left completely unexplained, and 'minutes' still has no semantic description.

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 ('Start a guided breathing exercise'), plus scope ('runs right in the chat', '1, 2 or 5 minutes', 'no video needed') that implicitly separates it from play_feed_video, start_experience and suggest_reset. An agent knows exactly what this does 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?

Extensive when-to-use guidance ('moments of stress, anxiety or overwhelm; nerves before a meeting...; trouble focusing...'), which is unusually concrete. It stops short of naming alternatives (e.g., when to use suggest_reset or start_experience instead) and gives no when-not-to-use conditions.

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