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

Annotations only declare it as non-read-only, destructive, and idempotent; the description goes well beyond that by explaining that in-flight rows finish and are charged, remaining work is skipped, and unused holds are returned. It also discloses that sweep_dispositions acts on already-rejected rows even after the run ended, which is exactly the kind of side effect an agent must know before invoking a destructive tool.

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?

The core behavior and the sweep option are front-loaded and efficient, but the trailing prompt-injection warning is generic boilerplate and the sentence fragment "Free." is cryptic and unstaked to anything. Both dilute an otherwise tight definition.

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 destructive mutation with no output schema, the description covers side effects, the optional sweep path, verification polling, and cost impact. It omits any statement about the response or error conditions when the run id is invalid or already 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 coverage is 100%, so the baseline would be 3, but the description earns more by adding the "even if the run already ended" qualifier to sweep_dispositions and by cross-referencing flow_run_id's origin (run_flow). It stops short of detailing what "move or delete" concretely means per row.

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?

"Stop a queued or running Flow run" gives a concrete verb plus resource and scopes which run states are affected. It does not, however, distinguish this tool from the sibling cancel_run, which an agent could easily confuse with 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?

The description clearly frames when to use it (queued or running runs) and when to reach for the optional sweep_dispositions path, including the non-obvious case of runs that already ended. It also gives the follow-up procedure (poll get_flow_run with wait_seconds). The one missing piece is guidance on choosing this over the sibling cancel_run.

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