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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds genuinely new behavioral context: the selection is 'Remembered on this connection,' disclosing session-scoped persistence that the annotations do not convey.

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, front-loaded with the action and its scope, with the lookup pointer in parentheses. Nothing is wasted and nothing needed is omitted.

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, annotation-covered state tool with no output schema, the description covers action, scope, valid-value source, and persistence. It is slightly thin on whether switching mid-session affects other pending state, but that is a marginal gap.

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% and the single 'company' param already says 'Company id or name.' The description goes beyond the schema by telling the agent where to obtain valid values (get_connection lists them), which is the one thing the schema does not provide.

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 verb+resource (switch/choose the company) and the exact consequence: it determines which company all Hub tools subsequently act on. It also names the sibling that enumerates valid values (get_connection), so an agent can distinguish it from the hub_* family without opening any schema.

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 phrase 'Hub tools act on' makes the usage context clear: call this before/among hub_* operations to scope them. It points to get_connection as the source of valid choices, but never states explicit when-not conditions or what happens to in-flight calls from the previous company.

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