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

Annotations already cover readOnly, idempotent, non-destructive, and closed-world; the description adds that only persisted data is returned (no live provider call) and that history is cursor-paginated, which is meaningful behavioral context beyond the annotations. It stops short of describing auth/ownership failure modes.

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?

Two tight sentences; the core scope is front-loaded and the 'saved data only' constraint follows immediately. No wasted wording.

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 usefully enumerates what comes back (action, stateVersion, audit history), but it leaves all four parameters unexplained and says nothing about paging direction or limits, leaving meaningful gaps for a 4-param read tool.

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, but it names none of the four parameters. 'cursor-paginated audit history' only faintly gestures at `before`/`limit` and gives no semantics for `actionId` (the required key) or `workspace`.

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: reading a single owned mapped action plus its stateVersion and paginated audit history. The singular 'one owned mapped action' implicitly separates it from the sibling list tool read_preparation_actions and from read_preparation_job, though no sibling is named explicitly.

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?

'Saved data only; no provider work' tells the agent this is a snapshot read rather than a live fetch, but it never says when to prefer this over read_preparation_actions or read_prepared_page_changes, nor what prerequisites (ownership, mapping) are required.

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