get_docker_stats

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

With no annotations, the description carries the full burden and does substantial work: it discloses the SSH transport, the one-shot (non-streaming) nature, the RUNNING-only filter, and the non-obvious privilege escalation path (sudo -n / doas -n when the login user is not root or in the docker group). It omits failure behavior (what happens if passwordless sudo is unavailable), whether the call is strictly read-only, and timeout semantics.

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 tight sentences with no filler; the core capability and its scope are front-loaded, and the escalation detail follows as supporting context. Every clause adds information.

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?

An output schema exists, so return values need no explanation, and the escalation behavior is well covered. However, for a 7-parameter SSH tool with zero annotation coverage, missing detail on authentication options, host-key acceptance, and timeout/failure behavior leaves meaningful gaps for correct invocation.

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 0% across 7 parameters, so the description must compensate. It adds real meaning for 'user' (the login user whose daemon access depends on root/docker-group membership) and for 'host' (remote Linux host over SSH), but leaves port, timeout, key_path, password, and accept_new_hostkey entirely unexplained — notably the host-key verification default, which materially affects whether the call succeeds.

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 ('Collects a one-shot docker stats snapshot') and scopes it precisely: CPU %, memory usage/limit, network and block I/O, PIDs, and only RUNNING containers. This is far more specific than the sibling names alone, though it never explicitly contrasts itself with tools like get_docker_ps_all or get_docker_inspect.

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 stated: 'one-shot snapshot' signals a point-in-time read rather than continuous monitoring, and 'remote Linux host via SSH' frames the deployment context. There is no explicit when-to-use/when-not guidance and no named alternative for container listing or per-container inspection.

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