env_switch

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

With no annotations, the description carries full responsibility and delivers: it discloses side effects (records pointer, marks face read-only), safety constraints (destructive verbs refused on main), and the non-destructive unconfirmed path. This is exemplary transparency for a state-changing tool.

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, no filler. The main action is front-loaded, and each subsequent sentence adds distinct behavioral detail without redundancy. Optimal length for the information conveyed.

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?

The description covers key behavioral aspects (read-only marking, destructive refusal, confirmation behavior) but leaves gaps: what happens when confirmed (presumably executes), what the returned plan contains, the meaning of 'P8', and the roles of workspaceId and idempotencyKey. Without an output schema or annotations, these omissions create a moderate 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 description coverage is 0% and the description only indirectly explains the 'confirmed' parameter via 'Unconfirmed, returns a plan and changes nothing'. It provides no meaning for 'workspaceId', 'name', or 'idempotencyKey'. The description fails to compensate for the complete lack of schema descriptions.

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 states a precise verb ('Set') and resource ('active environment for this face'), and adds distinguishing specifics: switching to a served/protected env ('main') records the pointer and marks read-only, while destructive verbs remain refused. This clearly separates it from sibling tools like env_create, env_copy, or env_reset.

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 implicitly tells when to use this tool (when you need to change the active environment) and explains the confirmation flow ('Unconfirmed, returns a plan and changes nothing'), which is critical usage context. It does not explicitly compare to alternatives like env_create or env_reset, but the uniqueness of 'switch' makes the context clear.

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