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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: it is a preview that does not run engines, returns three budget candidates (nominal, 10%, 20% reserve), and computes limits/blockers. That extra detail is meaningful even with annotations present.

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 with the key constraint (no arbitrary tools/external code) front-loaded. No filler, though it is dense and could benefit from clearer separation of inputs vs outputs.

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?

Given nine parameters, no output schema, and heavy domain complexity, the description is too thin. It should explain what 'items' represent, how uncertainty shapes candidates, and the meaning of min_success_rate, but it does not. It is complete at a high level but not for correct invocation.

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 0%, so nine parameters are documented only by names and types. The description mentions 'budgets', 'assumptions/permissions', and 'tools' but does not define what items, uncertainty, duration_model, or min_success_rate mean. It partially compensates but leaves most parameters semantically thin.

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 states a verb and outcome ('Preview robust scheduling... return up to three candidate budgets'), which is specific. But it doesn't differentiate plan_mission from the sibling build_robust_plan, which appears to do the same job. The core purpose is vague relative to the crowded planning family.

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?

It implies usage ('Preview... without running engines', 'No arbitrary tools or external code'), suggesting a dry-run planning call. But it never says when to use plan_mission instead of build_robust_plan, simulate_plan, or stress_test_observation. Usage is inferred, not guided.

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