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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=true, idempotentHint=true), and the description adds genuine context beyond them: stable device IDs are unaffected, duplicate names stay ambiguous, and a phone-owned screen propagates the new name to its clock and Settings only once connected. It does not say whether the prior name is recoverable or what permissions are required.

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, front-loaded with the core action, then selector caveat, then propagation detail. Every sentence carries information, though the clock/Settings sentence is the least essential of the three.

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 two-parameter mutation with an output schema already covering return values, this is nearly complete: purpose, selector semantics, and side-effect propagation are all present. The gap is around irreversibility and authorization requirements for a tool flagged destructiveHint=true.

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 0%, so the description carries the burden. It adds real meaning by implying the `device` argument is a stable device ID rather than a name (since duplicate names are ambiguous selectors) and that `name` is the account-visible label, but it omits the 1-128 character constraint and any format expectations.

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 specific verb and resource with scope: 'Changes the account-visible name of one authorized screen.' This cleanly separates it from read-side siblings like device_get_status or devices_list, though it never names an alternative operation.

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?

Usage is implied rather than stated: 'one authorized screen' signals a single-target precondition, and 'duplicate names remain ambiguous selectors' warns that name-based selection is unreliable. There is no explicit when-to-use versus when-not-to-use guidance or named alternative.

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