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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds genuinely useful context beyond that: work performed so far is preserved rather than discarded, and a waiting turn's review is what gets cancelled. It still doesn't say whether the operation is reversible or what state the turn ends in.

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?

One front-loaded sentence with two parallel clauses, no filler, and the outcome-bearing detail (work is kept) placed immediately after the verb.

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 one-parameter mutation with no output schema, the description covers both invocation states and the preservation semantics. What is missing is post-condition detail such as whether the turn can be resumed or is terminal.

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% and the single turn_id parameter is already documented as coming 'from send_message', so the schema carries the parameter burden. The description adds no further parameter meaning, which is the expected baseline for full coverage.

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 plus resource (stop a turn) and distinguishes two distinct states: a running turn versus a waiting turn's review. That is more precise than the title alone, though it never names the related siblings (cancel_generation, undo_turn, interject_turn) it could be confused with.

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?

The description implicitly defines when it applies by describing the two turn states it handles, but it offers no explicit exclusions or alternatives. An agent facing a stuck run has no guidance on stop_turn versus cancel_generation, retry_turn, or undo_turn.

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