fleet_snapshot

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

Without annotations the description carries the full burden, and it does disclose real behavior: output is persisted to the local state dir, changes are diffed against the previous snapshot, and it can be driven from cron. It still omits whether the tool touches the hosts (read-only vs mutating), any permission/auth requirements, runtime cost, and where the state dir lives.

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 core action, followed by scope and then the scheduling tip; every sentence serves a purpose. The long parenthetical enumeration of captured subsystems is dense but earns its place as scope definition.

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 tool with no output schema or annotations, the description covers purpose, captured scope, the reporting behavior, and scheduling. Remaining gaps are operational: state dir location, host-side impact, and how to retrieve past snapshots or diffs named by the sibling tools.

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 100%, so both 'reason' and 'target' are already documented in the schema; the baseline is 3. The description only indirectly enriches them, by implying the 'daily' reason value through the cron example, and adds no selector syntax or scoping detail beyond the schema.

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 plus resource: record host configuration state and report the diff since the previous snapshot, with the captured surface enumerated (packages, units, containers, ufw, ports, sshd, keys, cron, sysctl, certs, tracked files). That is far more concrete than a title restatement. It stops short of naming related siblings such as fleet_changes or snapshots_list, so an agent cannot tell from the text alone which one surfaces the history it just wrote.

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 a clear operational context: run it on a schedule (e.g. daily cron `mia call fleet_snapshot`) to build a change history. That tells the agent when this tool is the right one, namely a recurring baseline capture. No when-not guidance or explicit alternative is offered for ad-hoc inspection of existing snapshots or diffs.

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