docker_doctor

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

With no annotations provided, the description carries the full transparency burden. It explicitly says 'scans' and 'reports,' implying a read-only operation, and mentions the return of a clean-bill-of-health message. However, it does not directly state that the tool makes no modifications to containers, which would be clearer for a diagnostic 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?

The description is two concise sentences that front-load the purpose and then summarize the return behavior. The format is clean, with no irrelevant details, and the parameter explanations are separate, keeping the main description focused and scannable.

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?

Given a simple tool with two optional parameters and no nested objects, the description covers the core functionality adequately. It lists the key health issues detected and the return behavior, though it omits details about the output schema or any performance implications. Still, the context is sufficient for an agent to use the tool correctly.

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 provides only parameter names, types, and defaults, so the description adds essential meaning by explaining each threshold: 'CPU %% above which a running container is flagged' and 'memory %% of its limit above which a container is flagged.' This clarifies units and context beyond the bare schema, but lacks examples or edge-case handling details.

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 clearly states that the tool scans all containers and reports only those needing attention, listing specific conditions (OOM kills, restart loops, unhealthy health checks, crashes, high resource usage). It also mentions a clean-bill-of-health return, making the purpose unambiguous. The phrase 'instead of checking containers one by one' differentiates it from manual inspection.

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?

The description provides a clear usage hint: 'use this instead of checking containers one by one,' which tells the agent when to choose this tool over manual per-container checks. However, it does not explicitly reference specific sibling tools or enumerate scenarios where other tools might be preferred, so some context is implicit rather than stated.

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