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

Annotations (readOnlyHint=false, idempotentHint=true, openWorldHint=true, destructiveHint=false) cover the safety profile, and the description adds genuinely non-redundant behavior: confirmation typically takes 30-60 seconds, payment windows can expire, and the success payload contains download links plus license_pdf_url. It also prescribes the presentation order to the user, which no annotation conveys.

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?

Front-loads the purpose, then flows directly into the return shape, the pending path, the timing expectation, and the expiry fallback. Every sentence carries an instruction or a fact; nothing is 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, the description still enumerates the meaningful return values (license_issued status, download links, license_pdf_url) and the failure modes (pending, expired). An agent has everything needed to call this tool and act on its result.

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% and the schema already documents payment_id as 'the payment_id returned by initiate_license', so the description adds no syntax, format, or constraint information beyond it. Baseline 3 applies when the structured field does all the work for a single parameter.

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 and resource ('check whether a license payment has been confirmed on Base') and distinguishes itself from the sibling initiate_license by referring to it as the fallback for expired windows. An agent can route between verify_license and initiate_license from the description alone.

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?

Explicit when-to-use and what-to-do-next branches: poll again if the status is pending after the user confirms, and start a new license with initiate_license if the payment window is expired. It also names the alternative tool by name, which is exactly the sibling-routing guidance an agent needs.

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