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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior. The description adds meaningful traits beyond that: it streams native events via MCP progress, is a single composite call, performs no arbitrary tool generation, and returns distinct terminal statuses (inconclusive, blocked). That is genuine extra behavioral context.

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?

It is front-loaded with the core action and avoids padding, but the pivotal sentence is a dense stack of statistical qualifiers ('simultaneous 95% Monte Carlo lower bound meets the requested success target under independent uniform duration uncertainty') that is hard to parse at a glance.

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 9-param, no-annotated-output, composite orchestration tool, the description explains the algorithm and the result statuses but leaves the parameter surface almost entirely uncovered and gives no sense of the return shape or event payloads. Adequate for orientation, 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 coverage is 0% and there are 9 parameters, so the description carries the full burden. It gestures at the statistical model (95% Monte Carlo lower bound, independent uniform duration uncertainty, success target) and the 'up to three' candidate cap, but never explains seed, budget, samples, allowed_tools, or duration_model by name, leaving most parameters undocumented anywhere.

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 a concrete action (compare up to three task selections, select the highest-value candidate meeting a success target) and names the specific sibling tools it orchestrates (optimize_tasks, simulate_plan). It clearly conveys what the tool produces (a robust plan or an inconclusive/blocked status), though it never explicitly contrasts itself with plan_mission, another planning sibling.

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 gives useful internal guidance — 'use an exact bound instead of simulation when possible', reuse identical selections, and the fallback conditions for inconclusive/blocked. However, it does not say when an agent should choose build_robust_plan over optimize_tasks, simulate_plan, or plan_mission directly, which is the core routing decision.

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