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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavior beyond that: what the payload contains (messages + run), that `after_message_id` switches between full and incremental reads, and that an in-progress answer is surfaced via `still_working`/`retry_in_seconds` rather than blocking. It stops short of stating what happens if the rehearsal is unknown or finished.

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 sentence with no filler, front-loading the primary payload (messages) before the run metadata. The phrasing 'What a rehearsal has said' and the inline field names make it slightly harder to parse than a plain 'Returns ...' construction, 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?

With no output schema, the description must carry the return-value burden, and it does name the meaningful fields (messages, status, current card, still_working, retry_in_seconds). Gaps are minor for a read-only tool with full annotation coverage: no note on message ordering, volume, or error behavior for an unknown conversation_id.

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 100%, so both parameters are already documented and this sits at the baseline. The description adds one useful nuance the schema omits: the default when `after_message_id` is absent is all messages. Otherwise it restates the incremental-filter behavior the schema already provides.

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 the resource (a rehearsal created by `rehearse_flow`) and enumerates what is returned: messages plus run status, current card, and progress hints. The verb is implicit ('What a rehearsal has said') rather than an explicit 'read/get', and it never contrasts itself with lookalike siblings such as `read_conversation`, `check_flow`, or `list_flow_runs`, so sibling differentiation is left to the resource name.

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?

Usage is only implied: the mention of `still_working` with `retry_in_seconds` 'while an answer is coming' signals a polling pattern, which is a real hint. There is no explicit statement of when to call this versus `read_conversation` or `rehearse_flow`, and no prerequisite note that `conversation_id` must come from a prior `rehearse_flow` call (that exists only in the schema).

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