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

Annotations already flag destructive and idempotent, but the description adds real behavior: a single restart when running, scoping to the service's own variables, refusal semantics with the reason surfaced, and the Valet account prerequisite. It does not explain whether the restart interrupts in-flight work.

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?

Front-loaded with the core action and side effect, then progressively layers the refusal rules. Slightly dense with several clauses, but each sentence carries non-redundant operational information.

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?

With no output schema, the description compensates by describing response behavior: refusals name the holder and what frees it, and unknown names are reported without failing. Combined with full schema coverage, an agent has everything needed to invoke and interpret the call.

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 100%, so the schema already documents name, names, and org_name. The description adds no per-parameter syntax or format detail, only an oblique note that inherited org variables are untouched. Baseline 3 applies.

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 concrete verb (Remove) and resource (environment variables on an app or agent), plus the notable side effect of restarting the service. It is trivially distinguishable from set_env_vars and list_env_vars in the sibling list.

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 explicit when-not conditions: variables referenced by a connector/channel or set by a resource are refused, and it names the actual alternatives (destroy_channel for an owned channel, detach_resource for resource variables). It also tells the agent that removing an unset name is non-fatal.

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