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

Annotations already cover read-only and non-destructive behavior, but the description adds valuable context beyond them: it saves nothing, returns a draft for user review, and consumes one small AI call. It also clarifies that persistence happens only through a later create_link call.

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 front-loaded with a concrete purpose and examples, then follows immediately with the key behavioral constraint: it saves nothing. Every sentence contributes useful information without repetition.

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 draft-generating tool with no output schema, the description adequately explains the expected draft contents and the follow-up action. It does not specify the exact return shape or handling of ambiguous input, but the key workflow is clear.

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 all parameters. The description adds useful examples of what belongs in the description parameter, such as "Instagram bio to WhatsApp" and "a link for my van that opens the booking page," though it does not separately explain site_id or user_goal.

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 precise verb and resource: turn a plain request into a tracked-link draft. It enumerates the draft contents (address, destination, campaign tags, prefilled message) and explicitly distinguishes this from create_link.

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?

It gives explicit usage: use when the user describes a link in plain language, show the draft without saving, then call create_link with adjustments. The alternative sibling create_link is named with the condition for its use.

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