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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds value beyond those by disclosing deterministic behavior, the possibility of returning 'blockers', and the paid nature with a specific per-call price. No contradiction exists between the description and 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 description is compact at three sentences and front-loads the core purpose before exclusions and pricing. The phrase 'Intended for selection routing / quality unknown' is somewhat vague and adds limited value, but overall the description is efficient and free of padding.

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 no output schema and no parameter explanations, the description leaves important operational details missing: the exact structure of 'concrete blockers', how execution constraints combine with the graph, and what a successful response looks like. The pricing and scope exclusions help, but for a graph-validation tool of this complexity, more is needed.

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 carries the full burden for explaining parameters. It only vaguely references 'workflow dependencies' and 'execution constraints', which loosely map to edges and cost/latency limits but provides no concrete meaning for nodes, edges, max_total_cost, or max_total_latency_ms, nor how to structure the graph input.

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 specific verb and resource: 'Validates caller-supplied workflow dependencies and execution constraints' and names the outputs ('deterministic execution order or concrete blockers'). It also distinguishes itself from legal, identity, sanctions, and similar adjudication tools with an explicit exclusion. However, it does not differentiate this instance from the many sibling selection_routing_control_plane_* tools, leaving the purpose clear but sibling differentiation incomplete.

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 gives a broad usage context ('Intended for selection routing') and explicit negative guidance ('Do not use for legal, identity, sanctions, fraud, contractual, or regulatory adjudication'), plus cost information. It does not, however, tell the agent when to choose this tool over alternative control planes, routers, or validators such as workflow_dependency_validator or other selection_routing_* siblings.

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