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

Discloses non-obvious behavior the annotations don't carry: selection is session-scoped, the hosted server forgets it between calls, and the active template is cleared. There is mild tension with readOnlyHint=true since clearing a template is a state change, though it affects session state rather than stored data.

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 tight sentences, zero filler, with the core action stated first and the persistence caveat immediately after. Every clause carries information an agent needs.

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 single-parameter session tool with no output schema and a read-only annotation profile, the description covers the essential contract. Minor omissions remain: format of a valid site id and what happens if the id is unknown.

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 schema already documents `id`, but the description adds the meaningful nuance that `id` must be supplied on every call despite the session concept. That is real semantic value beyond the one-line schema description.

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?

Names a concrete verb and resource ("Set the active site for this session") and adds a scope fact — it clears any active template — that separates it from select_template behaviorally. It never names a sibling explicitly, so differentiation is inferred rather than stated.

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?

Gives a real usage instruction ("still pass `id` on every call") because state isn't persisted, which is genuinely actionable. However, it never says when to reach for this tool versus peers like select_template or list_sites, so the when-to-use guidance is only implied.

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