env_switch

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

Moving well beyond the single destructiveHint annotation, the description discloses real consequences: the pointer is recorded, the face becomes read-only on hosted envs, main stays writable, destructive env-wide verbs remain refused, and unconfirmed calls are dry-run plans. This is genuinely useful behavioral context; the only shortfall is missing auth/permission or reversibility notes.

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?

Four compact sentences with the core action front-loaded and the dry-run caveat last. It is efficient, though the parenthetical spec references (D135, P8) consume space without informing an external agent.

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 destructive mutation with no output schema and bare parameters, the description supplies good behavioral context and even a return hint ('returns a plan'). However, half the parameters (name, idempotencyKey) and any permission/reversibility detail remain undocumented, leaving the definition only partially complete.

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?

With 0% schema description coverage, the description carries the load. It effectively explains the 'confirmed' parameter's dry-run semantics ('Unconfirmed, returns a plan and changes nothing') and implies 'name' and 'workspaceId' via 'env' and 'this face', but never addresses 'idempotencyKey' or states parameter names directly, leaving gaps.

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 verb+resource 'Set the active environment' is unambiguous and naturally distinguishes this mutation from env_current/env_status/env_list reads and env_create/env_delete. However, opaque internal jargon ('this face', 'D135', 'served (hosted) env', 'main') is never decoded, slightly blurring the exact resource being changed.

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?

Embedded rules give partial guidance: switching to a hosted env marks the face read-only, and an unconfirmed call returns a plan without applying. But the description never states plainly when an agent should choose env_switch over env_create, env_reset, or env_copy, so usage is more implied than prescribed.

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