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

While annotations already declare readOnlyHint=true and idempotentHint=true, the description adds substantial behavioral context: it 'Starts no session and records no usage,' costs nothing, and runs no models. It thoroughly details what the return value includes (step order, roles, cost estimate, definition_sha) and explicitly notes what it does NOT return ('never hands back the definition itself'). This exceeds the baseline by providing comprehensive behavioral disclosure.

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 dense but relatively concise for the wealth of information it conveys. It's structured in two long sentences followed by a short usage directive. While packed with useful content, the first sentence is very long and could be seen as slightly unwieldy despite being information-dense. It front-loads the most important information (what it does and its cost-free nature) and ends with an actionable usage statement.

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 read-only preview tool with no output schema to explain return values, the description completely covers what's needed. It explains the cost implications, security posture (requires authentication), side-effect behavior, and the meaning of the definition_sha fingerprint. It even explains a limitation (doesn't return the definition itself) preemptively. With sibling alternatives like run_workflow and estimate_cost present, the description effectively positions this tool's role in the broader workflow.

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 100%, so the schema already documents both parameters well. The description complements the schema by adding context about how parameters behave in this tool: supplying values triggers validation, omitting them skips it. It also provides a concrete example ({"region": "EU"}) that illustrates the expected flat object format. Slight deduction because the description doesn't add extensive meaning for the 'workflow' parameter beyond what the schema states, but the validation semantics are helpful.

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: 'Preview what a workflow WOULD do, without running it.' It specifies the primary verb (preview) and resource (workflow), and distinguishes it from run_workflow by emphasizing it does not execute. The extensive detail about what it returns and its cost-free nature clearly differentiates it from siblings like run_workflow and estimate_cost.

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 explicitly states when to use this tool: 'Use before run_workflow to check a pipeline fits before spending on it.' It also provides exclusions by noting what it does NOT do ('Starts no session and records no usage'). The direct alternative (run_workflow) is named, and the context for using it over alternatives is clear.

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