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

Annotations already establish safety (readOnly, idempotent, non-destructive), and the description adds useful behavioral context: newest-first ordering and coverage of both delegated and scheduled tasks. It doesn't contradict annotations, and it doesn't overpromise writes or side effects.

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 tight sentences: the first front-loads the action, scope, and ordering, the second the filtering capability. No filler or repetition of schema details.

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 a full output schema, complete parameter descriptions, and annotations covering safety, nothing essential is missing. The description adds the account scope, ordering, and filter intent, making it sufficient for an agent to select and invoke correctly.

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% with helpful per-parameter descriptions, so the baseline applies. The description's 'Filter by status or task' restates what status and task_id already say in the schema without adding syntax, defaults, or pagination behavior.

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?

Description opens with a specific verb and resource ('List the account's task runs') and adds valuable ordering ('newest first'). It clearly delimits scope ('delegated jobs and scheduled tasks alike') and names the available filters ('by status or task'). This separates it from siblings like get_run, which targets a single run.

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 provides clear context for when to call this tool—when you want an account-level view of task runs, with optional filtering. It does not explicitly name alternative tools or exclusions, but the sibling list makes the boundary obvious (get_run for one run, cancel_run for cancellation, wait_for_run for blocking).

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