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

Annotations already cover read-only/idempotent/non-destructive, so the description's job is to add retrieval semantics — and it does, describing what 'list' returns (id, date, author) and that prompt_history includes restorable prompt snapshots. It stops short of disclosing pagination, ordering, or limits for the list action, which a caller would want to know.

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 purpose, then usage triggers, then a compact pipe-delimited action legend — every sentence contributes. The action list is dense but readable; the only mild cost is that the pipe notation compresses several distinct behaviors into one line.

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 responsibly sketches what each action returns (backup fields, prompt snapshots) and notes the restore-worthy snapshots. It leaves the exact response shape of 'latest' versus 'list' and the effect of 'full' mode to the schema and inference, so it is complete enough to call correctly but not fully specified.

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 only 33% (only 'mode' is documented), so the description must carry 'action' — and it does, defining all three enum values with their return contents. 'agentId' is self-evident and 'mode' is already covered by the schema, so the remaining gap is small.

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 ('Read the backups and prompt history of an agent') and immediately enumerates the three actions with what each returns, so the agent can map any read intent to a concrete action. The read framing also separates it cleanly from the sibling agent_backups_write without needing to name it.

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?

Gives concrete, actionable triggers: 'Check here before a risky change, or to find a version to go back to.' That tells the agent when to reach for this tool, but it never explicitly contrasts with agent_backups_write as the tool that actually performs a restore, leaving the next step implicit.

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