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

Annotations already declare readOnly=false, idempotent=true, destructive=false, but the description adds real operational context: exactly one alert on start, silent updates, one completion alert on end, plus a billing/rate-limit note (free accounts limited NEW streams per day; updates and final ping never charged). That is substantive disclosure beyond structured fields.

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?

Four tight sentences, front-loaded with the core action before lifecycle and pricing details. Every sentence carries distinct 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 not be explained, and the nested live_status object is fully documented in the schema. The description supplies the lifecycle and billing context an agent needs to drive the tool correctly across multiple calls.

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 baseline is 3, but the description adds lifecycle semantics for the key parameter by explaining that correlation_id is "the stream key" that must be reused across pings, and it defines the meaning of the state transitions. This meaningfully extends beyond the schema text.

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?

Names a precise verb set ("Start, update, or end"), the resource ("live progress card"), and the platform surface ("room members' lock screen / iOS Live Activity / Android live update"). This clearly separates it from the read-side sibling get_live_status without needing to name it.

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?

Explains the full lifecycle usage: reuse the same correlation_id per stream, "running" pings update silently, "done"/"failed" end the stream. However it never explicitly names the alternative read tool (get_live_status) or states when not to use this tool, so it stops short of full routing guidance.

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