cad_plugin

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

The description discloses critical security behavior: plugins run in the same process/trust domain without process-level sandboxing, install only loads entry-point plugins from installed distributions and rejects arbitrary module:attr imports. This meaningfully exceeds annotation context and helps agents judge risks; minor details like persistence of enable/disable state are not covered, but the key trust-boundary behavior is transparent.

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 action list is front-loaded, and the structure flows logically: overview, dispatch details, security, then when-not-to-use. It is a bit longer than strictly necessary due to bilingual repetition, but each section serves a distinct guidance purpose and is not bloated.

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 dispatcher tool with six actions, the description covers every action's semantics, the dangerous install edge case, the unresolved security hardening item, and usage boundaries. Since output schemas exist for each action variant, no return-format explanation is necessary; everything an agent needs to call it correctly is present.

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 100%, so the schema already documents all parameters. The description adds useful conceptual framing about install semantics and the trust boundary of module paths, but it doesn't provide additional format-level detail beyond the schema, so the baseline 3 is appropriate.

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 verb and resource: install, uninstall, list, enable, disable or inspect plugins. The opening sentence names every supported action, and the final line explicitly scopes the tool to plugin lifecycle management, distinguishing it from sibling tools that expose plugin capabilities.

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 provides a 'When not to use' note stating that actual plugin capabilities should be invoked via their registered MCP tools, not through cad_plugin. This gives the agent clear selection guidance and alternative routing, well beyond simple implied usage.

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