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

Beyond the destructive/idempotent annotations, the description discloses the actual removal timing: a pending change is dropped immediately, while a backup already held by the screen is removed at its next check-in. It also explicitly bounds the blast radius (current WiFi unaffected), which is exactly the context an agent needs before invoking a destructive 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 short sentences, front-loaded with the action and the originating sibling, then the deferred-removal semantics, then the safety boundary. No filler and nothing repeated from the title or annotations.

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 an output schema present, annotations covering safety, and the parameter documented in-schema, the description covers the remaining gap well by explaining deferred removal and the unaffected current network. It does not say what happens if no backup exists, though the idempotent hint largely covers that.

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% with a single device_id parameter already documented as coming from host.overview, so the schema carries the load. The description adds no further meaning about the parameter, which is acceptable at this coverage level but earns only the baseline.

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?

"Remove the backup WiFi set with host.screens.set_wifi" gives a specific verb (remove), a specific resource (backup WiFi), and ties it to the companion sibling that created it. An agent can separate this from host.screens.set_wifi without opening either schema.

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 makes clear this is the undo counterpart to host.screens.set_wifi and scopes the effect ("Its current WiFi is not affected"), which implicitly tells the agent this is not a full network reset. It stops short of an explicit when-to-use/when-not statement or naming an alternative for clearing the active network.

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