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

Annotations mark it as non-read-only, destructive and open-world; the description earns credit by explaining why — it acts under the agent's permissions, can message people, and consumes agent credits. The 15-second wait followed by 'returns running true while the step goes on' discloses the async/partial-result behavior, which annotations cannot express.

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 dense sentences, no waste: side effects and costs come first, timing and return shape second. Every clause carries information an agent needs before invoking.

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 mutation tool with no output schema, the description covers side effects, credit cost, timeout, and the returned 'running' flag, which is close to complete. It stops short of telling the agent how to follow up on a still-running step (no polling tool is named), leaving a small gap.

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% and both parameters (agent_id, goal_id) are documented in-schema with their source lists. The description adds no further meaning about parameter formats or constraints, so the baseline 3 applies.

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 concrete verb and resource: 'Work one step of a goal now.' The 'outside its interval' phrasing separates it from scheduled goal execution, though the distinction from near-siblings like run_agent_task_now and run_agent_trigger_now is left implicit (only the noun 'goal' differentiates).

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 implies when to use it ('now, outside its interval') and implies an alternative (the goal's normal schedule), but never names a sibling tool or states a when-not condition. An agent must infer that run_agent_task_now / run_agent_trigger_now are the analogues for other objects.

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