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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context: it is deterministic ('deterministic execution order') and is a paid resource ($0.002 USD per call). These traits are not in the annotations and help the agent anticipate side effects and costs. No contradiction with 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 two sentences, front-loaded with the core purpose. It efficiently includes exclusions and cost information without unnecessary fluff. The structure is clear and scannable, though it could benefit from a brief parameter mapping.

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 tool that accepts a graph (nodes/edges) with constraints, the description lacks essential details: how to construct nodes and edges, what 'execution order' means, what blockers look like, and how the constraints interact. With no output schema and many similar siblings, the description does not provide enough to call the tool correctly without further investigation.

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 compensate. It gives only a high-level hint that 'workflow dependencies' correspond to nodes/edges and 'execution constraints' to max_total_cost and max_total_latency_ms, but it does not explain the structure of nodes/edges (e.g., the meaning of cost, enabled, latency_ms) or the semantics of the constraints. The description adds minimal value beyond the schema.

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 clearly states the tool's purpose: validating workflow dependencies and execution constraints and returning a deterministic execution order or blockers. This is a specific verb-resource combination. However, it does not explicitly differentiate itself from the many sibling orchestration tools (e.g., workflow_dependency_validator, execution_safety_orchestration_*), relying only on the phrase 'reliability quality / trust unknown' to imply scope.

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 context ('reliability quality / trust unknown') and lists exclusions (legal, identity, sanctions, fraud, contractual, regulatory), but it does not suggest alternative tools for those exclusions or explain when to choose this tool over similar ones. There is no explicit 'use X instead' guidance, so the agent must infer applicability.

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