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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description still adds genuinely new behavioral context: lingering is opt-in via stay=true, and the experience is untimed and unscored, which sets agent expectations that the annotations cannot express. It stops short of describing what a scene yields or what happens with a stale identifier.

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?

Three short, front-loaded sentences with the core action first and parameter guidance second. Nothing is wasted, though the closing 'No timers or scores' is slightly cryptic and could be folded into the linger sentence for tighter structure.

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 two-parameter read tool with full annotation coverage and no output schema, the description covers purpose, the source of the required id, and the optional flag. The main residual gap is the return shape and behavior on an invalid or expired scene id, which the agent would have to discover at call time.

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%, so the description carries the param burden and does so reasonably: 'scene' is defined as an identifier from a prior choice, and 'stay' is defined as a linger flag. The regex constraint and 80-char cap on 'scene' are left unexplained, but the semantics of both parameters are conveyed.

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 gives a specific verb+resource ('Read a Warm Bath scene') and names the exact input it consumes ('scene identifier returned by a previous choice'). However, it never distinguishes this tool from the sibling read_experience, leaving the agent to guess why a dedicated Warm Bath reader exists alongside a generic one.

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 supplies one real precondition — the scene id must come from a previous choice — which is useful provenance. But there is no statement of when to pick this over read_experience or list_experiences, and no mention of error/failure conditions, so usage is only implied.

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