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

Annotations already declare readOnlyHint=true and destructiveHint=false, establishing a non-mutating operation. The description adds the useful detail that the configuration is credential-free and protocol-specific (MCP or A2A), but doesn't disclose return format, whether it performs network calls, or any other behavioral constraints.

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?

One sentence with no filler, front-loaded with the verb and then constraints. Every word earns its place.

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 simple one-parameter tool, the description covers the main purpose and the client constraint, but with no output schema it doesn't describe the shape or format of the returned configuration. The mention of MCP or A2A hints at the output but leaves format details implicit.

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 single 'client' parameter is an enum with self-explanatory values, so the schema largely documents itself. The description reinforces that the client must be supported but adds no explanation of each enum value or expected format; with 0% schema description coverage, it contributes only marginally.

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 uses a specific verb ('Generate') with a clear resource ('connection configuration'), and adds meaningful constraints: credential-free, MCP or A2A, supported client. This distinguishes it from sibling tools like get_connection_bundle, which retrieves an existing bundle rather than generating a config.

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 implies the tool is for producing a client configuration for a supported agent client, but it doesn't explicitly state when to choose this over alternatives or list exclusions. With siblings like get_connection_bundle and discover_* tools, there is no routing guidance, leaving some inference to the agent.

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