stop_run

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

With no annotations, the description carries the whole burden; it does disclose one genuinely useful behavioral trait — partial results are preserved ('best answer so far is kept'). It omits whether stopping is idempotent, what happens if the run is already finished, and whether this is synchronous or asynchronous.

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?

Two short sentences with the action front-loaded and the key side effect second — no waste. It is efficient, though its brevity contributes to the specification gaps noted elsewhere.

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 result-preservation note covers the main outcome. However, for a lifecycle-mutating tool with no annotations and an undocumented id parameter, more about preconditions and post-conditions would be needed to call it confidently.

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?

The single required parameter 'id' has 0% schema description coverage and is never mentioned in the description. The agent gets no clarification on whether it is a run ID, job ID, or something else, so the description fails to compensate for the schema gap.

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 + resource ('Stop a run'), which is enough for an agent to distinguish it from start_run and run_status. It does not explicitly contrast with siblings, but the name/semantics make the distinction obvious.

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?

No guidance on when to stop versus when to poll with run_status or fetch results with get_answer. The agent must infer the workflow (e.g., check status first, then stop) entirely on its own.

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