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

Annotations already declare destructive=true, idempotent=true and readOnly=false, and the description adds meaningful context beyond them: no billing or settlement occurs, and the call is a silent no-op unless confirm=true. What is missing is the failure mode for an invalid or already-cancelled callId.

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, all load-bearing, with the scope constraint front-loaded ahead of the caveat. The clause 'that cleanup path bills the live session' is compressed jargon that costs the reader a re-read.

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 no output schema, the definition covers the critical quirks: no charge, no effect without confirm, and no effect on live calls. Only the callId sourcing and error/repeat-call behavior remain unstated.

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 has to carry both parameters. It effectively defines confirm by declaring the tool does nothing unless it is true, but callId is only indirectly characterized through 'invite you created' — no format, lookup source, or error behavior is given for it.

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?

The description gives a specific verb and resource ('Cancels an incoming invite you created') and explicitly negates the implication of its own name by saying a connected call is not ended here. That correction is genuinely useful, but the phrase 'incoming invite you created' is internally odd and leaves the exact object being cancelled slightly ambiguous.

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?

It clearly states the condition under which this is the wrong tool ('A connected call is not ended here') and explains why. It stops short of naming the alternative path for terminating a live session, so the agent knows when not to use it but not what to use instead.

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