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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds genuinely useful context beyond them: it returns 'native receipts and 95% sampling bounds' and warns that 'Completed means assessed, not safe.' The latter is a meaningful semantic caveat. It stops short of describing failure modes or rate/timeout behavior.

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?

Four tight sentences with the action front-loaded and no filler. However, the compressed jargon ('advertised bindings', 'native receipts') trades clarity for brevity, so efficiency is slightly at the expense of comprehension.

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 5-parameter, nested-object tool with 0% schema coverage and no output schema, the description is too thin: it never explains the required goals/available inputs or the constraint controls. It partially covers the output ('receipts', '95% sampling bounds') but leaves the input contract opaque.

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% across 5 parameters with nested objects, so the description must carry the load. It mentions 'engine inputs and explicit uncertainty' and repeats the 1–150 km/h route speed that the schema already enforces, but says nothing about goals, available, or the constraints object (max_steps, local_only, allowed_tools, max_search_states). It does not compensate for the coverage gap.

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 verb 'run' plus the resource 'task-selection/route-to-duration risk chains' gives a nominally specific purpose, but the phrasing is dense domain jargon that an agent cannot easily map to a concrete action. It gestures at scope ('approved ... chains only') but does not clearly distinguish this from siblings such as run_route_policy, compose_capabilities, or build_robust_plan.

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?

'Run approved ... chains only' states a precondition but no when-to-use versus alternatives. 'Other paths use advertised bindings' hints at routing but is too vague to tell an agent which sibling to pick instead. No exclusions or hand-offs are stated explicitly.

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