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

The annotations declare a non-read-only, open-world, non-idempotent, non-destructive write, and the description adds real information beyond that: execution recurs every interval_minutes up to max_iterations, actions run under the agent's own permissions, and each step consumes agent credits. The side effect of possibly messaging people is a meaningful disclosure. What's missing is whether the goal starts running immediately on creation or only at the first interval, which makes a duplicate call (non-idempotent) hard for the agent to reason about.

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?

Three short sentences with no filler, front-loading what the tool does and then layering the operational traits (cadence, iteration cap, permissions, credits). Every sentence carries distinct information.

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 seven-parameter write tool and no output schema, the description covers the essential behavior an agent needs: autonomy, recurrence, cost, and permission scope. It doesn't say what comes back (a goal id for later update/archive calls) or whether the goal activates immediately, which would be useful given the sibling set of goal-management tools.

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 only 14% for seven parameters, so the description should carry more weight, and it does explain the two scheduling parameters (interval_minutes as the cadence, max_iterations as the cap). It says nothing about objective, plan, success_criteria, title, and their relationship — for example, whether plan steps are actually executed or are only advisory — leaving most of the schema undocumented in both places.

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 first sentence, "Give an agent a goal to pursue on its own," names a specific action and resource that maps cleanly to the tool name, and the autonomous-pursuit framing separates it from one-shot siblings like run_agent_goal_now or schedule_agent_task. It never names those alternatives explicitly, though, and it doesn't distinguish itself from create_org_goal.

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 — whenever an agent should pursue something autonomously on a recurring interval — by spelling out the recurring cadence and iteration cap. It gives no explicit when-not guidance and doesn't mention update_agent_goal, archive_agent_goal, run_agent_goal_now, or create_org_goal, so the agent is left to infer which of these similar siblings to pick.

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