host_docker

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

With no annotations, the description carries the full behavioral burden and falls short. It never states that the call is read-only or side-effect free, and the word 'restarts' is genuinely ambiguous — it could mean reporting restart counts or triggering restarts, a distinction that materially changes safe usage.

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 compact sentence with no filler, and the covered subdomains are front-loaded. It loses a point only because the fragment omits any verb, which reduces rather than improves clarity.

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?

There is no output schema and no annotations, so the description should explain what a call returns; it partially does by listing state, image, restarts, and disk usage, but omits return shape, aggregation across containers/projects, and whether anything is mutated. Adequate but incomplete for a tool with zero structured behavioral support.

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% for the single 'host' parameter, including the pointer to fleet_hosts, so the schema does the work. The description adds nothing about the host parameter or how it is resolved, which fits the baseline 3 for a fully documented, one-parameter tool.

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?

It names a resource (Docker on a host) and enumerates the subdomains it covers (containers, compose projects, disk usage), but it is a bare noun phrase with no verb, so an agent cannot tell whether it reads/inspects Docker state or acts on it. It is distinguishable from siblings like host_services_discover or host_inspect only by the Docker keyword.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternative tools such as host_inspect, host_services_discover, or disk_cleanup that overlap in scope. The agent must infer that this is the Docker-specific inspection path.

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