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

Beyond the destructiveHint/idempotentHint/openWorldHint annotations, the description discloses the permission required (screen.cast), the propagation latency ('screens update within seconds'), and partial-failure semantics: unsupported or approval-gated screens are skipped and counted via notShared/needsApproval while the rest still change. That skip-and-count behavior is exactly the kind of outcome an agent cannot infer from destructiveHint=true alone.

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?

Labeled sections (When to use / When NOT to use / What to know / Parameters) front-load the routing decision, and the worked example is compact. It is dense and slightly long, with the parameter block partly restating schema field names, but almost every line carries non-redundant 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?

For a destructive, idempotent bulk-mutation tool, the description covers selection semantics, clearing behavior, bulk partial-failure outcomes, auth requirements, and latency. Return values are covered by the existing output schema, so nothing an agent needs in order to invoke this correctly is missing.

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%, so the baseline would be 3, but the description adds real meaning: screenId/screenIds/nodeId combine into a single union set with at least one required, nodeId expands to every screen at and under it up to 1000, contentKind null clears playback and is only legal with exactly one screen and no nodeId, and contentId originates from list_items. A concrete example call reinforces the combination rules.

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 its scope: 'Set what screens play by default until it is changed again.' The persistence clause immediately separates it from a temporary takeover, and the when-to-use line enumerates the target shapes (one screen, a list, a location subtree).

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?

Explicit when-to-use and when-NOT-to-use sections name the two decisive alternatives: start_takeover for self-terminating takeovers and update_items for changing playlist contents. Each alternative comes with the condition that selects it, and the parallel hint ('every screen playing it follows') explains the consequence of picking wrong.

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