Refresh the inventory snapshot for every host in a fleet

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

Beyond annotations, the description discloses concrete side effects: it connects to every accessible effective member host, collects live system fields, and overwrites the stored latest-only snapshot. This explains the mutation and access-dependent scope without contradicting the readOnlyHint/destructiveHint annotations.

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 sentences deliver the purpose first, then the mechanism and side effects. Every phrase adds information—scope, collected fields, and overwrite behavior—with no filler or repetition.

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 one-parameter side-effecting tool this is usable: it states target scope and the data written. However, with no output schema it does not disclose what the call returns, such as success/failure summary or per-host results, or behavior when some hosts are inaccessible, leaving completion semantics partly to the agent's assumption.

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?

The schema describes only an integer id with 0% parameter description coverage, and the description never states that id identifies the fleet. The fleet connection is inferable from the title, but for a low-coverage schema the description should explicitly map id to a fleet identifier.

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 opens with a specific verb and resource: 'Refresh the inventory snapshot for every host in a fleet.' It adds concrete detail—connects to accessible effective member hosts, collects OS/kernel/arch/hostname/uptime, and overwrites the latest-only snapshot—which clearly distinguishes it from siblings like reading the last-known snapshot or running commands across a fleet.

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 implied rather than explicit: the name and 'Refresh' indicate when to call it, and the description gives scope ('every effective member host the caller has view-level access to'). However, it does not name alternatives such as termix_fleets_read_last_known_inventory_snapshot_fleets or state when NOT to refresh, such as when a read-only lookup is sufficient.

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