close

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

Annotations declare readOnlyHint=false and destructiveHint=false. The description adds context that closing does not affect running containers and that connections are rebuilt lazily. This provides useful behavioral insight beyond the annotations, though it doesn't disclose potential side effects like loss of state or rate limits.

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 well-structured: first sentence states the action, second provides usage guidance, third gives parameter details. It front-loads the core purpose. While concise, the parameter section adds unnecessary detail that contradicts the schema, slightly detracting from conciseness.

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 the low complexity and lack of output schema (though returns bool is mentioned), the description covers purpose, usage, and parameter intent. However, the parameter contradiction undermines completeness, and it doesn't address edge cases like closing a non-existent connection. It is adequate but has clear gaps.

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 defines no parameters (empty object, 100% coverage), but the description states 'args: host - host label to close; omit to close every pooled client'. This directly contradicts the schema, misleading the agent. The description adds no valid meaning and instead introduces a false parameter.

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 the tool closes and drops pooled Docker client connections, with lazy rebuild on next use. It distinguishes itself from the sibling 'reconnect' tool by specifying that reconnect immediately re-establishes the connection. The purpose is specific and 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?

The description explicitly says 'Use this to force a stale or errored connection to be discarded' and advises 'Prefer `reconnect` when you want to immediately re-establish the connection'. This provides clear when-to-use and when-not-to-use guidance, along with an alternative tool name.

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