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

Annotations already declare readOnly/idempotent/non-destructive/no-open-world, so the safety profile is covered; the description goes further by disclosing inputs to omit (durations), numeric operating envelopes (1–150 km/h, 1–1440 min budget, 100–20000 samples, 1–32 legs), the recompute-and-execute behavior in Rust, and the important caveat that 'Completed means the assessment ran, not that the deadline is safe'. It does not address failures, compile cost, or runtime, but adds substantive context beyond the annotations.

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?

The purpose is front-loaded in the first sentence and each subsequent sentence carries non-redundant information (usage constraint, route-path requirements, ceil formula, numeric bounds, disclaimers, return shape). It is dense and jargon-heavy for a single paragraph, but there is little filler to remove given the tool's complexity.

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 complex graph-execution tool with no output schema and 0% schema coverage, the description supplies the return shape (engine result, risk assessment, 95% Hoeffding interval, native events), the two supported graph paths, and their input constraints. It is largely self-sufficient, with the main remaining gap being the meaning of the goals/available/constraints inputs.

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 the description must carry the burden. It does explain adapters['route_durations.v1'].speed_kmh (1–150), the simulate_plan configuration knobs (budget, uncertainty, samples, seed) and the requirement to omit durations, but it never explains what goes in goals, available, or the constraints block (max_steps, local_only, allowed_tools, max_search_states, max_structural_cost), leaving several top-level 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?

Names a specific action (recompile and execute) on a specific resource (the approved optimize_tasks → selected_durations.v1 → simulate_plan / route_optimizer → route_durations.v1 → simulate_plan graph path) in Rust. It also explicitly distinguishes itself from sibling tools by naming simulate_plan, optimize_tasks and route_optimizer and stating that other graph paths must use their advertised tool or stay planning-only.

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?

Gives a clear usage condition (only 'approved' graph paths) and a real exclusion (other graph paths must use their existing tool or remain planning-only), which routes the agent away from misuse. It does not define what 'approved' means or which sibling to call for the unsupported cases, so it stops short of explicit alternatives.

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