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

Annotations already disclose readOnlyHint=false and idempotentHint=true, so the write and repeat-safety profile is covered. The description adds real value beyond that by explaining the persistence model — the choice is 'kept on the connection' and applies to every session using it — which the annotations cannot express. It does not say what happens to a previously set default or whether other sessions are disrupted immediately.

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 tight sentences with zero filler; the primary effect is front-loaded, followed by the id source and then the alternative. Every sentence 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 one-parameter, no-output tool, the description covers what it does, where the id comes from, the scope of the persisted state (whole connection, all sessions), and the per-call alternative. No return value explanation is needed since there is no output schema.

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 `app` parameter's id semantics are already documented and the baseline is 3. The description goes slightly beyond by explaining the downstream effect of this value (later calls omitting `app` act on it) and its relationship to the per-call `app` argument on other tools.

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+effect: 'Make an app the default for this connection.' This is clearly distinct from list_apps, get_app, update_app, and create_app, since it sets a connection-scoped default rather than reading or mutating an app record.

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?

Explicitly names the alternative ('pass `app` on a single call instead when you only need one app briefly') and the condition under which to prefer it, and states the prerequisite source for the id ('from list_apps'). Nothing about when to choose this tool is left to inference.

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