cad_connect

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

The description discloses a genuinely important behavioral trait beyond the annotations: it is stateful and mutates how all subsequent calls are routed. The annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) only imply a non-read-only, non-idempotent operation; the routing effect is the real value added. It still omits edge behavior such as what happens if processId is stale or the process exits.

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?

Two compact sentences: the action is front-loaded and the second sentence justifies it without redundancy. Nothing is padding.

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 one-parameter, no-output-schema tool the description covers what it does and why, which is close to sufficient. The remaining gap is discoverability of the required processId, which neither the schema nor the description addresses.

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 description coverage is 0% for the single required parameter, so the description carries the full burden and adds nothing about processId. It never says where the value comes from (presumably cad_instances) or what form it takes, leaving an agent to guess at the most critical input.

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?

States a specific action and target ("Bind subsequent MCP calls to one specific AutoCAD process") plus the rationale (avoiding routing to the wrong drawing). It clearly reads as a session-scoping tool distinct from cad_command or cad_draw, but it never names the sibling that supplies the processId (cad_instances) or contrasts itself with cad_view/cad_status.

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 gives an implicit trigger condition ("when multiple instances are running") that tells the agent when binding matters, which is better than nothing. However, there is no explicit when-not guidance, no mention of how to discover the correct process, and no statement about whether the binding persists or can be released.

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