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

Annotations already indicate a mutation (readOnlyHint=false), idempotency, and non-destructiveness. The description adds valuable context: requires owner:sandbox sign-in, uses Stripe TEST mode and isolated orders, never charges real money or files with a county, and does not establish ownership or eligibility. This is rich behavioral context beyond annotations, though it does not describe the return value or post-start flow.

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 sentences, front-loaded with purpose and followed by essential constraints. Every sentence adds value, though the density of disclaimers could be slightly better organized for readability.

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?

The description covers purpose, safety, and auth, which is substantial for a mutation tool with no output schema. However, it leaves critical gaps: parameter meanings are largely unexplained, and it does not indicate what the agent should do after starting the checkout (e.g., use complete_tax_sandbox_order).

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?

With 0% schema description coverage, the description must explain the four parameters. It only hints at address_or_pidn ('one source-backed property') and service ('appeal or property-record service'), but does not define county_key, idempotency_key, or clarify the enum values (appeal vs. microtx). Most parameter semantics are missing.

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?

States a specific verb ('Start') and resource ('test-only appeal or property-record service checkout') with clear scope ('for one source-backed property'). Distinguishes itself from siblings like audit_property_tax or complete_tax_sandbox_order by emphasizing test-only and sandbox, though it does not name alternatives explicitly.

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 phrase 'explicitly requested' and disclaimers ('does not establish ownership, eligibility, savings or an open appeal window') imply when to use this tool and when to use other tools for those checks. However, no explicit alternatives are named, and there is no direct guidance on when-not to use or which sibling to choose instead.

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