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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered without the description doing any work. The description adds only that the run is 'hosted' and that resume can carry a revised budget, but says nothing about irreversible state transitions, whether abort on an already-aborted run is a no-op, or what a caller receives back.

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 sentences, zero filler, front-loaded with the action set and the resource. Nothing in the text is redundant with the title or padded.

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?

With no output schema the description should ideally say what comes back (e.g., updated run state), and it should note the precondition that the target run exists and is in a controllable state. Still, it covers all three actions plus the one conditional parameter, which is sufficient for a simple three-action control tool whose annotations and schema are rich.

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 action enum, budget deprecation notes, and run_id provenance are all documented in the schema itself. The description's one parameter-adjacent line ('Resume may supply a revised budget') restates the budget schema description rather than adding format, constraint, or interaction detail. Baseline 3 applies when the schema carries the load.

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 names three concrete verbs (pause, resume, abort) against a specific resource ('hosted research run'), so an agent immediately knows this is the lifecycle-control tool rather than a read tool like run_status or a creation tool like start_run. It stops short of naming any sibling explicitly or stating which run states each action applies to.

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?

There is no when-to-use or when-not-to-use guidance: nothing says the run must be in-progress to pause, that abort is terminal (that fact lives only in the schema enum), or when rerun_from is preferable to resume. The only conditional statement ('Resume may supply a revised budget') is parameter guidance, not usage routing.

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