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

Annotations declare destructiveHint=true and openWorldHint=true, but the description adds real behavioral context beyond them: the stream key is removed, a later set_live_activity_stream with the same key starts a fresh Activity, and ending remotely consumes the device's ActivityKit push budget. That budget/lifecycle detail is exactly the kind of non-obvious consequence an agent needs.

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 action, then routing to the alternative, then a caution. Every sentence carries distinct decision-relevant information with no filler.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The description fills the remaining gaps: lifecycle semantics, the key-removal consequence, and push-budget cost.

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 tags, alert, action, metadata, content_state, and stream_key thoroughly. The description adds no parameter-level detail beyond what the schema provides, so the 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 specific verb and resource ('End the current Live Activity for a managed stream') plus the concrete side effect of removing the stream key. It is immediately distinguishable from siblings like get_live_activity, list_live_activities, and pause_live_activity_stream.

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 an explicit when-to-use condition ('when the tracked work is finished') and names the alternative for the opposite case ('to stop updates temporarily and keep the key, use pause_live_activity_stream'). It even adds a when-not-to-use warning against repeatedly ending and recreating a stream.

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