system_reconnect

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

Beyond annotations (readOnlyHint false, destructiveHint false), the description discloses the validation-before-swap behavior, that the old client is only closed on success, and that it cannot retarget daemons. It also specifies the return shape. This provides substantial behavioral context not present in annotations.

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 detailed but efficient, with purpose front-loaded and limitations/alternatives clearly separated. It is longer than strictly necessary but every sentence adds value. No fluff or repetition. The only minor issue is the misleading host mention, which slightly disrupts 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?

For a zero-parameter tool with no output schema, the description covers purpose, behavior, limitations, alternatives, and return shape. It lacks error handling details but that is not critical here. The only gap is the inconsistent host reference, which introduces confusion rather than completeness.

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 input schema has zero parameters, so baseline is 4. However, the description mentions 'when host is omitted', implying a host parameter that does not exist in the schema. This is misleading and could cause an agent to attempt passing a host argument. The description actively adds incorrect parameter information, so a 2 is warranted.

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 states a specific action (rebuild a pooled Docker client) with a clear purpose (recover a wedged connection) and resource. It distinguishes itself from siblings by explicitly naming system_close (closes without rebuilding) and host_list (shows endpoints), making the tool's scope unambiguous.

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?

It explicitly states when to use (recover wedged connection) and when not to (cannot retarget to different daemon, edit config and restart instead). It names alternatives (system_close, host_list) and clarifies what they do differently. This leaves no inference needed.

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