fleet_discover

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

With no annotations, the description carries the full behavioral burden. It does disclose the data sources (local tailscale status, Remnawave panel) and the shape of the results, which is genuinely useful context. However, it never states that the operation is read-only, whether it writes the 'ready YAML' to disk, or what permissions/network access it needs – meaningful gaps for a zero-annotation tool.

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?

A single front-loaded sentence with the verb and sources up front and a colon-delimited list of outputs. Dense but every clause carries information; no filler or restatement of the name.

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 must convey return content, and it does so by enumerating the three result categories. Combined with the named data sources, an agent has enough to call it and interpret results; only the read-only/write-side-effect question remains unanswered.

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 tool takes no parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter information is missing or misleading.

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 ('cross-check') and concrete resources: the inventory, the tailnet via local `tailscale status`, and the Remnawave panel. It also enumerates what it surfaces (missing nodes with ready YAML, offline/unknown hosts, panel node state), so the agent knows this is a reconciliation/discovery operation. It never names or contrasts with the closest siblings (fleet_audit, fleet_status, tailnet_devices), so it falls short of a 5.

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 by the cross-check framing – you'd call this when inventory and reality may have drifted apart – but there is no explicit when-to-use, when-not-to-use, or alternative (e.g. fleet_audit vs this). The agent must infer the trigger condition from the verb alone.

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