system_logout

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

Goes beyond annotations by disclosing that it reaches into a private docker-py attribute and degrades to clearing nothing if that internal structure changes. Also clarifies impact: it mutates only the in-memory cache, not persistent state. This is exactly the kind of behavioral context annotations cannot provide.

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?

Though longer than simple examples, every sentence earns its place. It opens with a one-line summary, then provides necessary caveats, parameter behavior, return format, and technical risk in a well-organized structure. No fluff or repetition.

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?

Covers all aspects a caller needs: operation semantics, side effects, non-effects, parameter behavior, edge cases (no registry), return value format, and a degradation caveat. Given there is no output schema, providing the return dict structure is essential and done well.

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 only provides type/default with 0% coverage. The description fully compensates: explains what 'registry' means ('Registry key to clear, or None'), how the Docker Hub key is stored ('docker.io'), and the requirement that the key must match system_login. This turns an opaque parameter into a well-understood one.

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 opens with a specific verb and object: 'Clear cached registry credentials from this server's in-memory Docker client.' It immediately distinguishes this from system_login and clarifies that it is not a true logout but a cache-clearing operation, preventing confusion with the sibling tools.

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?

Explicitly explains when to use it (to drop cached credentials), when not (does NOT touch the host's ~/.docker/config.json), and even mentions alternatives: 'system_close/system_reconnect also clear it by discarding the client.' Also specifies how to use the optional registry parameter and the Docker Hub key nuance.

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