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

Annotations declare destructiveHint=true, but the description adds substantial behavioral detail: widgets keep config and fall back to demo data, the connection itself is not deleted, and explicit recovery steps (refresh_report, get_widget_data) are given. This goes well beyond the structured annotations and is highly informative.

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?

Three sentences, each earning its place: the main action, the critical caveat, and the recovery workflow. The most important information is front-loaded, with no filler or redundancy.

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 tool with only two parameters, full schema coverage, an output schema, and clear behavioral disclosure, the description is complete. It tells the agent what happens, what to expect after the call, and how to verify the result. No gaps remain for correct invocation.

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%, with both parameters already described in the input schema (client_id from list_clients, datasource_id enum with examples). The description references datasource_id in the workflow but adds no new semantic meaning beyond the schema, so 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 uses a specific verb-resource pairing ('Detach a connected datasource from a client') and explicitly distinguishes itself from a related operation ('Does not delete the connection itself'). This clearly separates it from siblings like delete_connection and link_datasource.

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 gives clear context for when to use the tool (when you want to stop widgets from pulling from a connection while keeping the connection) and provides post-unlink steps. However, it does not explicitly name alternative tools or state the condition to choose this over delete_connection, 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.