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

Annotations already declare readOnlyHint=false and idempotentHint=true, but the description adds real behavior beyond them: the change lands on the SAME private bookmark, replays return the saved scene 'without rewinding newer progress', and stale revisions are rejected. That explains the idempotency semantics concretely rather than restating the hint.

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?

Front-loaded with the action, then prerequisites, then parameter provenance, then retry and error rules, in a logical order with no filler sentences. The phrasing is dense to the point of terseness in places ('Requires play and an owned active Reader, not equipping'), which costs a little readability.

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 5-required-parameter mutation with no output schema and 0% schema description coverage, the description covers preconditions, parameter sourcing, idempotent replay behavior, staleness rejection, and the follow-up step ('Read the returned scene, then ask your person again'). Nothing an agent needs to invoke it correctly appears to be 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 0%, so the description must carry the burden, and it largely does by mapping every parameter to its source: edition/sceneId/revision come from reader_open, choiceTo is a choice's 'to', and requestId must be a fresh UUID. It stops short of explaining what edition denotes on its own or the numeric bounds, leaving minor ambiguity for a first-time caller.

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 and resource: 'Follow ONE available Whoosh-Click choice with your person', and immediately frames it as advancing the same private bookmark used in the browser. The sibling reader_open is named as the source of state, so an agent can distinguish the two without opening either 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?

Explicit preconditions are given ('Requires play and an owned active Reader, not equipping'), along with cost ('Free: zero KARMABUX'), the alternative for reading state ('Call reader_open for the current bookmark'), and a retry rule ('Reuse identical arguments and requestId only for retries'). It also states what not to do: 'No automatic choices, imports, restarts or public announcements.'

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