fleet_status

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

No annotations are provided, so the description carries the full burden, and it does substantial work: probing happens over ssh in parallel, per-host metric set is enumerated, open issue codes are summarized rather than detailed, and with target=all non-fleet tailnet devices are added with Linux machines probed under the default ssh user and others reported by online state. It omits timing/timeout/rate-limit and credential behavior, which is the remaining gap.

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 purpose and dense with useful detail; nearly every clause carries information. It is a long em-dash-chained sentence, so readability suffers slightly, but there is little filler.

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 and no annotations, the description must cover both behavior and return content, and it enumerates the returned metrics and issue codes well enough to set expectations. It still does not describe the response structure (per-host objects, error/offline representation) or failure handling, leaving a modest gap for a probe tool that depends on SSH reachability.

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 baseline is 3, but the description goes beyond the schema by explaining the semantic interaction between the two parameters: 'target all' triggers tailnet device enumeration and the 'tailnet' flag governs it, plus how those extra devices are handled. That is real added meaning, not a restatement.

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 ('one-screen health of the fleet') and enumerates exactly what is collected per host (uptime, load, memory, disk, updates/reboot, container, certs, Tailscale, panel, users online). It also explicitly routes the agent to the sibling that owns the detailed view ('details: fleet_audit'), so it is distinguishable from fleet_hosts/fleet_audit without opening a schema.

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 clear context for when this is the right tool (a single-screen fleet health summary) and names the alternative for the deeper case ('details: fleet_audit'). It does not state explicit exclusions or prerequisites (e.g. whether SSH reachability or credentials are required), so it stops short of full when/when-not guidance.

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